© 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. 10-GEMMASCOPE-RES-131K
    7. 68954
    Prev
    Next
    INDEX
    Explanations

    selectively spaced

    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
     
    -2.38
     semelh
    -2.17
     fenô
    -2.09
    ,;
    -1.92
     recém
    -1.89
    の影響
    -1.82
     incluindo
    -1.80
     nobre
    -1.77
     DURING
    -1.75
     complexo
    -1.75
    POSITIVE LOGITS
     with
    2.56
     at
    2.02
    Sziasztok
    1.85
     from
    1.77
     on
    1.76
     pertanian
    1.73
     or
    1.72
     without
    1.71
     hidupnya
    1.68
    Rozmiar
    1.68
    Activations Density 1.028%

    No Known Activations