© 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. 47629
    Prev
    Next
    INDEX
    Explanations

    pushback or retaliation

    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
    orgung
    -0.75
     отре
    -0.75
     montañas
    -0.72
    chtete
    -0.71
    hammed
    -0.71
     кризи
    -0.71
    𝒊
    -0.71
    pogon
    -0.69
     hommes
    -0.68
    ètes
    -0.68
    POSITIVE LOGITS
     back
    3.36
    back
    2.06
    Back
    1.89
     Back
    1.78
     zurück
    1.77
     terug
    1.55
    BACK
    1.55
     BACK
    1.50
    回
    1.41
    バック
    1.30
    Activations Density 0.018%

    No Known Activations