© 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. 44300
    Prev
    Next
    INDEX
    Explanations

    translation, transfer, or movement

    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
    -
    -3.11
    \
    -3.00
    ↵↵
    -2.81
    </strong>
    -2.67
    _
    -2.64
    1
    -2.56
    ("
    -2.56
    P
    -2.38
    ter
    -2.34
    /
    -2.34
    POSITIVE LOGITS
     dotato
    2.72
    鲮
    2.66
    摃
    2.59
     Gegenteil
    2.33
    嘜
    2.30
    歃
    2.30
     Herzens
    2.28
    .’
    2.25
    .’”
    2.23
     predecess
    2.19
    Activations Density 0.007%

    No Known Activations