© 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. 119566
    Prev
    Next
    INDEX
    Explanations

    familial

    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
    ↵
    -2.31
    謖
    -2.09
    </h3>
    -2.08
    泔
    -2.03
    valg
    -1.97
    倥
    -1.97
    dámské
    -1.94
     voldoende
    -1.90
    ה
    -1.90
    ökning
    -1.87
    POSITIVE LOGITS
    at
    2.84
    ᡵ
    2.30
    of
    2.30
    賔
    2.27
    /
    2.19
     besonder
    2.11
    }
    2.03
    by
    2.02
     Thus
    1.96
    f
    1.95
    Activations Density 0.004%

    No Known Activations