© 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. 48490
    Prev
    Next
    INDEX
    Explanations

    crime investigation stories

    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
    eaked
    -0.98
    *}
    -0.85
     bloemen
    -0.85
    ートン
    -0.84
     Urinary
    -0.83
    hv
    -0.80
    necked
    -0.80
     surveyor
    -0.79
    фу
    -0.79
    études
    -0.79
    POSITIVE LOGITS
     investigation
    2.61
     investigating
    2.59
     investigate
    2.52
     investigations
    2.05
    investig
    2.03
     investigated
    1.98
     Investigation
    1.95
    investigation
    1.94
    Investig
    1.91
     investigates
    1.88
    Activations Density 0.022%

    No Known Activations