© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128522
    Prev
    Next
    INDEX
    Explanations

    range or approximation

    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
     and
    -2.08
    i
    -1.90
    ↵
    -1.80
    ねえ
    -1.80
    </em>
    -1.77
    ’
    -1.77
    Rather
    -1.77
    好像是
    -1.75
    ーと
    -1.73
    </h2>
    -1.67
    POSITIVE LOGITS
    媜
    2.30
    饧
    1.90
     sincerely
    1.76
     of
    1.76
    苼
    1.74
    metido
    1.73
     gracefully
    1.71
     londres
    1.70
    咴
    1.70
    眚
    1.69
    Activations Density 0.010%

    No Known Activations