© 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. 21576
    Prev
    Next
    INDEX
    Explanations

    other [noun]

    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
     as
    -1.65
     and
    -1.53
     yıl
    -1.29
     itself
    -1.26
     or
    -1.26
    Forgery
    -1.20
    geslacht
    -1.20
     Aufenthalts
    -1.20
     result
    -1.20
    tividade
    -1.20
    POSITIVE LOGITS
     dvě
    1.55
    typically
    1.35
    oped
    1.32
    worldly
    1.31
     белого
    1.30
    TWO
    1.29
    нимание
    1.28
    츨
    1.28
     avendo
    1.28
    two
    1.27
    Activations Density 0.101%

    No Known Activations