© 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. 39974
    Prev
    Next
    INDEX
    Explanations

    H. followed by name

    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
     their
    -1.74
     perintah
    -1.59
    entistas
    -1.58
    örté
    -1.55
    ',
    -1.54
    ",
    -1.52
     Shirts
    -1.51
     reputable
    -1.51
    pisah
    -1.48
     '
    -1.46
    POSITIVE LOGITS
    owulf
    1.57
    ’).
    1.48
    ्य
    1.38
    ⑊
    1.38
    situation
    1.37
    THERE
    1.35
     you
    1.35
    debate
    1.33
     himo
    1.31
    invention
    1.30
    Activations Density 0.021%

    No Known Activations