© 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. 117616
    Prev
    Next
    INDEX
    Explanations

    creative commons license

    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
     things
    -0.86
    蔵庫
    -0.79
     Pfar
    -0.77
    getLogin
    -0.76
     ripet
    -0.75
     její
    -0.73
     bộ
    -0.73
    resentação
    -0.71
     tried
    -0.71
    ImageView
    -0.71
    POSITIVE LOGITS
     licensee
    1.00
     open
    0.96
    open
    0.95
    OPEN
    0.94
    Open
    0.94
    开放
    0.86
    This
    0.84
     terbuka
    0.81
    payer
    0.81
     відкри
    0.81
    Activations Density 0.039%

    No Known Activations