© 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. 7294
    Prev
    Next
    INDEX
    Explanations

    names, faces, voices, character

    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
     of
    -1.88
    っていない
    -1.71
     for
    -1.64
     who
    -1.59
    -1.55
     it
    -1.55
    -1.41
    fordshire
    -1.38
    ってない
    -1.30
     hiyo
    -1.27
    POSITIVE LOGITS
     Berücksich
    1.57
     tendría
    1.52
     Unglück
    1.45
     somente
    1.37
    if
    1.36
     Voraussetzung
    1.34
     Zustimmung
    1.31
    さらに
    1.31
    дное
    1.31
    дная
    1.30
    Activations Density 0.077%

    No Known Activations