© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32490
    Prev
    Next
    INDEX
    Explanations

    official said

    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
    ಂಡ
    -0.93
    ・・
    -0.87
    Ⓖ
    -0.86
    ⋯
    -0.85
    ⫹
    -0.85
    eners
    -0.84
    ESSO
    -0.82
    Jegy
    -0.82
    XR
    -0.82
    Comparison
    -0.82
    POSITIVE LOGITS
     declined
    3.92
     refused
    3.09
     decline
    2.67
     declining
    2.30
     declines
    2.27
     refuse
    2.25
     refusing
    2.23
     refuses
    2.22
     wouldn
    2.03
    decl
    2.02
    Activations Density 0.026%

    No Known Activations