© 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. 45298
    Prev
    Next
    INDEX
    Explanations

    until followed by a time or condition

    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
    \
    -1.59
     bald
    -1.48
    いつも
    -1.45
    裄
    -1.42
    9
    -1.42
    jä
    -1.41
    ⠀⠀⠀⠀⠀⠀⠀⠀
    -1.39
    to
    -1.38
     douleur
    -1.38
     prognosis
    -1.38
    POSITIVE LOGITS
    棡
    1.67
     comisiones
    1.62
     you
    1.62
    and
    1.61
    ALERT
    1.59
     habia
    1.55
    ࿆
    1.55
    OTHY
    1.53
     paisajes
    1.53
     verkau
    1.53
    Activations Density 0.016%

    No Known Activations