© 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. 129407
    Prev
    Next
    INDEX
    Explanations

    physical characteristics

    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
     бампер
    -1.41
     including
    -1.38
     such
    -1.24
     каба
    -1.19
     expressly
    -1.18
    Források
    -1.16
    efois
    -1.16
    れば
    -1.16
     others
    -1.15
     出演
    -1.15
    POSITIVE LOGITS
     ویتامین
    1.50
     ὅ
    1.31
     when
    1.28
    Slightly
    1.27
     perú
    1.26
    ÜN
    1.25
     lavable
    1.24
     lorsqu
    1.20
    messi
    1.19
    capace
    1.18
    Activations Density 0.039%

    No Known Activations