© 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. 31029
    Prev
    Next
    INDEX
    Explanations

    license description

    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
     acha
    -0.81
     دام
    -0.79
     gob
    -0.77
    capace
    -0.76
    ײ
    -0.75
    issance
    -0.75
     Diversion
    -0.75
    🆖
    -0.73
    把她
    -0.73
     pared
    -0.73
    POSITIVE LOGITS
    actions
    1.32
     actions
    1.24
    leading
    1.07
     leading
    1.02
    toolbar
    1.00
    Leading
    0.97
    Actions
    0.94
     action
    0.92
     ações
    0.91
     действие
    0.88
    Activations Density 0.001%

    No Known Activations