© 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. 65146
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    。
    -1.29
    —-
    -1.27
    ————
    -1.16
    where
    -1.07
     ongeveer
    -1.06
    —
    -1.06
    .-(
    -1.05
    Why
    -1.02
    const
    -1.02
    ———
    -1.02
    POSITIVE LOGITS
     enlightening
    1.41
     zapato
    1.28
     escalating
    1.27
     contentious
    1.27
     unquestionably
    1.26
     unequivocally
    1.26
     appalling
    1.20
     hindering
    1.20
     expressly
    1.20
     crippling
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.