© 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. 93259
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and licenses

    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
    toBe
    -0.91
    رز
    -0.84
    (':
    -0.79
     куртка
    -0.76
    pples
    -0.76
     "}
    -0.75
    )}^{
    -0.73
     Solicitors
    -0.73
    arjo
    -0.71
    ⁷
    -0.71
    POSITIVE LOGITS
     deterioro
    0.73
     Gebrauch
    0.73
    Continues
    0.71
    はない
    0.70
    aujourd
    0.68
    Ⱦ
    0.67
    tières
    0.66
    navigationItem
    0.65
     ezen
    0.65
    uary
    0.64
    Activations Density 0.025%

    No Known Activations