© 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. 128673
    Prev
    Next
    INDEX
    Explanations

    technical modules and media metadata

    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
     \
    -1.58
    ことも
    -1.58
    N
    -1.57
    事も
    -1.48
    為に
    -1.42
    K
    -1.41
    L
    -1.39
     about
    -1.38
    J
    -1.32
    D
    -1.31
    POSITIVE LOGITS
    <bos>
    1.68
     作り方
    1.48
    ppings
    1.45
     étan
    1.41
    ztes
    1.40
     lavable
    1.40
    壁紙
    1.39
     Verenig
    1.38
     PLAYERS
    1.32
     PLATES
    1.30
    Activations Density 0.010%

    No Known Activations