© 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. 22-GEMMASCOPE-RES-131K
    7. 128258
    Prev
    Next
    INDEX
    Explanations

    digit words

    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_22/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
    ཥ
    -1.88
     quí
    -1.73
     rè
    -1.69
     chô
    -1.65
     remé
    -1.63
    ਞ
    -1.59
     bê
    -1.55
     élas
    -1.53
     créer
    -1.52
    ſſi
    -1.52
    POSITIVE LOGITS
     and
    1.87
     for
    1.86
     after
    1.76
     during
    1.70
     while
    1.63
    r
    1.61
     if
    1.53
    k
    1.51
     as
    1.49
    p
    1.48
    Activations Density 0.064%

    No Known Activations