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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129867
    Prev
    Next
    INDEX
    Explanations

    my essay, Q:, the effect

    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
     only
    -1.58
     with
    -1.45
     for
    -1.37
     both
    -1.34
     in
    -1.31
     after
    -1.29
     while
    -1.28
     just
    -1.22
     Surprisingly
    -1.20
     because
    -1.15
    POSITIVE LOGITS
     énorme
    1.22
    ⎯
    1.18
    nare
    1.16
    泐
    1.16
     SEVEN
    1.13
    isters
    1.13
    urface
    1.12
     gigantic
    1.11
    ᅚ
    1.11
     onze
    1.10
    Activations Density 0.000%

    No Known Activations