© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106561
    Prev
    Next
    INDEX
    Explanations

    extreme enthusiasm or obsession

    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_34/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
    textTheme
    -0.84
    InOut
    -0.83
    toHave
    -0.82
    rahat
    -0.79
    обеди
    -0.78
    routeProvider
    -0.77
     AMEND
    -0.77
    autogui
    -0.75
    şem
    -0.74
     carelessness
    -0.73
    POSITIVE LOGITS
     crazy
    3.38
    crazy
    3.00
    Crazy
    2.91
     Crazy
    2.67
     obsessed
    2.36
     mad
    2.30
    mad
    2.02
     CRA
    1.95
    疯狂
    1.92
     nuts
    1.83
    Activations Density 0.053%

    No Known Activations