© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84179
    Prev
    Next
    INDEX
    Explanations

    copyright statements2. license information3. XML/plist/Project Sdk tags4. `All rights reserved`5. `This program is free software`6. `This software is provided 'as-is'`7. `MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE`Let's look at `TOKENS_AFTER_MAX_ACTIVATING_TOKEN`: `This\n<\nSee\n<\nit\nRed\nwith\n<\nThis\nThis\n<\nMER`The tokens `This` and `<` appear multiple times. `MER` is also there. commercial licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Despite
    -2.05
    angkap
    -1.97
     Terbaik
    -1.96
     what
    -1.92
     melap
    -1.88
    What
    -1.77
    ——”
    -1.77
     pengantin
    -1.75
     Tempat
    -1.75
     rajut
    -1.74
    POSITIVE LOGITS
    U
    2.44
    P
    2.34
    ar
    2.14
    L
    2.06
    am
    2.06
    H
    2.03
    J
    2.03
    M
    2.03
    j
    2.00
    a
    1.99
    Activations Density 0.001%

    No Known Activations