© 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. 79934
    Prev
    Next
    INDEX
    Explanations

    urls in code

    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
     lainnya
    -0.96
    izoen
    -0.93
     that
    -0.91
     любого
    -0.91
     Betrieb
    -0.91
     другой
    -0.90
     delgado
    -0.90
     コ
    -0.90
    çoit
    -0.89
    另一种
    -0.89
    POSITIVE LOGITS
    等は
    1.13
     and
    1.12
    mässig
    1.10
    zló
    1.05
     האָ
    0.98
     stuttering
    0.96
     ].
    0.94
     ווע
    0.93
     podrob
    0.93
     nuestro
    0.93
    Activations Density 0.003%

    No Known Activations