© 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. 93021
    Prev
    Next
    INDEX
    Explanations

    checking problem conditions

    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
    を使用した
    -1.12
    只不过
    -1.06
     zwier
    -1.05
     Reised
    -1.05
    notag
    -1.05
     visualización
    -1.05
    varen
    -1.04
    roh
    -1.03
     vidrio
    -1.03
     diferentes
    -1.02
    POSITIVE LOGITS
     such
    1.35
     by
    1.30
     information
    1.18
     or
    1.16
     quickly
    1.14
     efficiently
    1.13
    чами
    1.10
     enfans
    1.10
    Também
    1.08
     cheaply
    1.06
    Activations Density 0.048%

    No Known Activations