© 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. 84100
    Prev
    Next
    INDEX
    Explanations

    metaphorical usage and description

    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
    ?"
    -2.64
    ！"
    -2.41
    !"
    -2.39
    遹
    -2.28
    نامج
    -2.23
    ());
    -2.22
    鯪
    -2.22
    要点
    -2.19
    ’,
    -2.17
    เกง
    -2.17
    POSITIVE LOGITS
    .
    3.34
    0
    3.34
    5
    2.67
    剷
    2.22
    actéristi
    2.20
    逦
    2.20
    “
    2.19
    ってしまった
    2.17
    嚇
    2.17
    终究
    2.16
    Activations Density 0.004%

    No Known Activations