© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38385
    Prev
    Next
    INDEX
    Explanations

    words followed by specific prepositions/punctuation

    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
     although
    -1.57
    CCIÓN
    -1.45
     fleste
    -1.42
     pouze
    -1.42
     whilst
    -1.38
    excellents
    -1.38
     disminuir
    -1.30
     opravdu
    -1.29
     Amongst
    -1.27
    ত্র
    -1.27
    POSITIVE LOGITS
     ELEVATION
    1.29
     –
    1.29
     Assn
    1.23
    沕
    1.23
     originale
    1.20
     EXHIBIT
    1.19
     constate
    1.19
    奬
    1.19
     heretofore
    1.18
     PRECISION
    1.16
    Activations Density 0.050%

    No Known Activations