© 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. 21007
    Prev
    Next
    INDEX
    Explanations

    cesium, CsComputer Science, Csgo

    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
     estratégica
    -2.98
    洐
    -2.84
    浹
    -2.73
     consentimento
    -2.70
    婓
    -2.69
    媗
    -2.61
    ᯾
    -2.58
    蚨
    -2.52
    秫
    -2.45
     acrí
    -2.39
    POSITIVE LOGITS
     It
    3.27
    "
    3.05
    or
    2.80
    If
    2.48
    ();
    2.39
    >
    2.30
    (\
    2.25
    where
    2.19
    on
    2.17
    ly
    2.16
    Activations Density 0.005%

    No Known Activations