© 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. 93606
    Prev
    Next
    INDEX
    Explanations

    read more link

    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
     halle
    -0.71
    halle
    -0.70
    看了一眼
    -0.68
     Pursuit
    -0.68
    rave
    -0.67
    youts
    -0.66
     swar
    -0.66
    ridge
    -0.66
     trow
    -0.65
     остался
    -0.65
    POSITIVE LOGITS
     ह
    0.74
    rieu
    0.71
    ước
    0.67
     对象
    0.66
    бар
    0.66
    ;&#
    0.66
     falsos
    0.66
    ழ
    0.66
     बना
    0.65
    AndEndTag
    0.65
    Activations Density 0.041%

    No Known Activations