© 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. 22-GEMMASCOPE-RES-131K
    7. 34136
    Prev
    Next
    INDEX
    Explanations

    programming tasks and invention

    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_22/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
     hilft
    -1.21
    }],
    -1.19
     baisse
    -1.08
    西瓜
    -1.04
     &.
    -1.02
    --"
    -1.01
     igreja
    -0.99
    —"
    -0.99
     wraz
    -0.99
    Elaboración
    -0.98
    POSITIVE LOGITS
     of
    1.20
    ᴘ
    1.14
    𝑚
    1.13
    𝑛
    1.11
    tivité
    1.06
     फ
    0.98
     område
    0.98
     (
    0.98
    ization
    0.98
    suggest
    0.93
    Activations Density 0.000%

    No Known Activations