© 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. 117296
    Prev
    Next
    INDEX
    Explanations

    legal citations and code structures

    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
     nadal
    -0.84
    вица
    -0.82
    fören
    -0.81
     vem
    -0.76
     recepto
    -0.75
    klä
    -0.75
     Gespräch
    -0.74
     Sorten
    -0.74
    exe
    -0.73
     पढ़
    -0.73
    POSITIVE LOGITS
     Arkansas
    0.84
    ルイ
    0.79
    odori
    0.77
    Hå
    0.76
     Escape
    0.76
    uker
    0.74
     evacu
    0.73
     וגם
    0.73
    ñor
    0.72
    arelli
    0.72
    Activations Density 0.001%

    No Known Activations