© 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. 10-GEMMASCOPE-RES-131K
    7. 44971
    Prev
    Next
    INDEX
    Explanations

    javascript module exports

    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_10/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
    垆
    -1.80
     وضعیت
    -1.74
     jamás
    -1.64
     estuviera
    -1.63
     beide
    -1.60
    ぐらい
    -1.59
    ("");
    -1.58
    --;
    -1.58
    ʹ
    -1.58
    '"
    -1.55
    POSITIVE LOGITS
     will
    2.08
    伱
    2.06
     commonly
    1.74
     includes
    1.73
     keeping
    1.70
     each
    1.66
     time
    1.66
    dası
    1.66
     these
    1.64
     ensure
    1.63
    Activations Density 0.002%

    No Known Activations