© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12587
    Prev
    Next
    INDEX
    Explanations

    to a point where

    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
    ématiques
    -1.14
    ｴ
    -1.04
    already
    -1.04
    ரும்
    -1.03
     histoires
    -1.03
    насе
    -1.02
    gungen
    -1.00
     princesse
    -0.98
    volent
    -0.96
    выя
    -0.96
    POSITIVE LOGITS
     where
    2.39
     need
    1.53
     needing
    1.52
     needed
    1.48
     can
    1.38
    where
    1.31
     that
    1.23
     required
    1.23
     when
    1.22
     able
    1.21
    Activations Density 0.024%

    No Known Activations