© 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. 10-GEMMASCOPE-RES-131K
    7. 13162
    Prev
    Next
    INDEX
    Explanations

    states or conditions with modifiers

    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_10/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
     because
    -2.14
     during
    -1.92
     it
    -1.85
     three
    -1.72
     jajaja
    -1.69
    婓
    -1.67
     after
    -1.67
     two
    -1.61
     hän
    -1.60
     allows
    -1.55
    POSITIVE LOGITS
     VERY
    2.16
     extremely
    2.13
     largely
    2.03
     strikingly
    1.98
     incredibly
    1.88
     somewhat
    1.86
     significantly
    1.84
    ཿ
    1.82
     extremamente
    1.82
     remarkably
    1.80
    Activations Density 0.172%

    No Known Activations