© 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. 49174
    Prev
    Next
    INDEX
    Explanations

    DOM manipulation and web documents

    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
    стую
    -0.71
     rant
    -0.70
    Encore
    -0.70
     delicate
    -0.68
     levou
    -0.66
    GLfloat
    -0.65
    Merhaba
    -0.65
     abraço
    -0.65
     Control
    -0.65
    iteur
    -0.65
    POSITIVE LOGITS
     Verder
    0.91
    Dom
    0.80
    Connor
    0.80
     sportifs
    0.76
    ცი
    0.75
    hh
    0.75
     BUDGET
    0.75
     bpy
    0.75
    季节
    0.73
    rya
    0.73
    Activations Density 0.017%

    No Known Activations