© 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. 39592
    Prev
    Next
    INDEX
    Explanations

    pluck, plump, choose, extract

    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
    u
    -2.70
     With
    -2.36
    ve
    -2.27
     Lately
    -2.22
    ro
    -2.20
    va
    -2.16
    In
    -2.16
     Initially
    -2.14
    」、
    -2.13
     Originally
    -2.11
    POSITIVE LOGITS
     I
    2.58
    驺
    2.27
    沕
    2.25
    犼
    2.20
    鱨
    2.11
    えっ
    2.11
     filhos
    2.09
     segurando
    2.08
     olhando
    2.08
     sentada
    2.06
    Activations Density 0.005%

    No Known Activations