© 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. 129263
    Prev
    Next
    INDEX
    Explanations

    Effect of, High quality, Numerical codes, Q:

    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
     baratas
    -1.56
    signable
    -1.35
    éfonos
    -1.30
    ״
    -1.26
    rably
    -1.25
    ynchron
    -1.25
     exceptionnel
    -1.23
    ꈊ
    -1.23
     what
    -1.23
    lihatan
    -1.22
    POSITIVE LOGITS
    p
    1.22
    er
    1.20
     Unterscheidung
    1.15
    2
    1.13
     presenza
    1.09
     is
    1.09
    f
    1.09
     moron
    1.09
    i
    1.09
    j
    1.07
    Activations Density 0.000%

    No Known Activations