© 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. 10-GEMMASCOPE-RES-131K
    7. 101406
    Prev
    Next
    INDEX
    Explanations

    past number of years

    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
     日記
    -1.68
     When
    -1.67
    ného
    -1.65
    鏐
    -1.63
    はなく
    -1.63
    颪
    -1.63
     tailles
    -1.62
     rodzaj
    -1.59
    four
    -1.56
     This
    -1.52
    POSITIVE LOGITS
    、
    1.67
     '
    1.64
     sincerely
    1.51
    </em>
    1.48
    '
    1.43
    0
    1.43
    ৄ
    1.43
    少
    1.38
    釓
    1.36
     newspapers
    1.34
    Activations Density 0.030%

    No Known Activations