© 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. 39822
    Prev
    Next
    INDEX
    Explanations

    to date

    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
    </i>
    -1.68
     and
    -1.56
     vesel
    -1.54
    ợn
    -1.46
    رحلة
    -1.45
    Being
    -1.44
    ()',
    -1.41
    iconSize
    -1.41
    basicConfig
    -1.41
    '],
    -1.39
    POSITIVE LOGITS
     egna
    1.55
    ol
    1.49
     I
    1.43
    ld
    1.38
    li
    1.32
    ts
    1.31
    ia
    1.30
     onslaught
    1.30
    ate
    1.30
    or
    1.30
    Activations Density 0.014%

    No Known Activations