© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204201
    Prev
    Next
    INDEX
    Explanations

    lists of concepts or terms

    np_acts-logits-general · gemini-2.5-flash-lite

    custom contexts and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accom
    0.50
    ihe
    0.46
    kih
    0.46
    した後
    0.45
     Bahadur
    0.45
    </h2>
    0.44
    directories
    0.44
    λαν
    0.43
    暨
    0.43
    klar
    0.43
    POSITIVE LOGITS
    প
    0.48
    йдз
    0.46
    ьте
    0.46
     postgres
    0.46
    ()+
    0.46
     creencias
    0.44
    ቢያ
    0.43
    ন্টে
    0.43
    ()-
    0.42
    Scaled
    0.42
    Activations Density 0.001%

    No Known Activations