© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13128
    Prev
    Next
    INDEX
    Explanations

    code intents and redirects

    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
     nowa
    -1.00
    LIO
    -0.97
     adresu
    -0.93
     Tomáš
    -0.93
    mesas
    -0.93
     sufre
    -0.93
    anía
    -0.91
    ischen
    -0.91
    ität
    -0.90
    ösen
    -0.90
    POSITIVE LOGITS
    Don
    1.11
     you
    1.09
    Here
    1.04
     ještě
    1.02
    You
    1.00
    Unser
    0.95
    wyżs
    0.95
     empê
    0.93
    Did
    0.92
     можно
    0.92
    Activations Density 0.001%

    No Known Activations