© 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. 48672
    Prev
    Next
    INDEX
    Explanations

    code declarations and comments

    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
     eigenes
    -0.82
     zapis
    -0.80
     Vertrag
    -0.77
    🫤
    -0.76
    Ї
    -0.76
    ⋙
    -0.75
     tailles
    -0.75
     artikkelen
    -0.74
     φυσ
    -0.74
    England
    -0.74
    POSITIVE LOGITS
     QString
    0.86
     QLabel
    0.83
    сторо
    0.83
     upacara
    0.83
    pleft
    0.81
     stil
    0.80
     HOLD
    0.78
    ifiz
    0.78
     intitu
    0.77
     irmã
    0.77
    Activations Density 0.001%

    No Known Activations