© 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. 78746
    Prev
    Next
    INDEX
    Explanations

    camp, kitsch, drama

    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
     الحديث
    -0.84
    FieldError
    -0.82
    ovsk
    -0.80
    貼
    -0.79
    icidal
    -0.79
     veno
    -0.77
     Niedersachsen
    -0.75
     необхідно
    -0.74
     melancho
    -0.74
    siert
    -0.74
    POSITIVE LOGITS
     exaggerated
    2.02
     exaggeration
    1.93
     exaggerate
    1.76
     theat
    1.63
     flamboyant
    1.59
     theatrical
    1.53
     exagger
    1.53
     extravagance
    1.52
     exager
    1.51
     extravagant
    1.43
    Activations Density 0.053%

    No Known Activations