© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67018
    Prev
    Next
    INDEX
    Explanations

    `index` retrieval and `update` information

    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
    N
    -1.73
     of
    -1.66
    L
    -1.62
    H
    -1.56
    Y
    -1.52
    D
    -1.48
    際に
    -1.48
    ことも
    -1.47
    K
    -1.47
    G
    -1.44
    POSITIVE LOGITS
    <bos>
    1.66
     herido
    1.56
    <0xA3>
    1.54
    ledad
    1.53
    hoku
    1.48
    ⛦
    1.43
    greja
    1.43
     NACIONAL
    1.41
    dienne
    1.41
    tidumbre
    1.39
    Activations Density 0.010%

    No Known Activations