© 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. 34-GEMMASCOPE-RES-131K
    7. 82797
    Prev
    Next
    INDEX
    Explanations

    FS Earl Thomas

    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_34/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
    dsc
    -0.81
     Oregon
    -0.80
    Proximity
    -0.78
    removal
    -0.73
    Removal
    -0.71
    鈴
    -0.70
    Skull
    -0.70
     zerstört
    -0.69
    lire
    -0.68
     impurities
    -0.68
    POSITIVE LOGITS
    Více
    0.84
     RID
    0.80
     secco
    0.79
    Proč
    0.79
     compiti
    0.79
    vermectin
    0.79
     epid
    0.76
    useEffect
    0.76
    nargs
    0.76
    írit
    0.75
    Activations Density 0.009%

    No Known Activations