© 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. 57680
    Prev
    Next
    INDEX
    Explanations

    quickly becoming, long been, PAX cargo

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

    introducing clauses or new thoughts

    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
    манов
    0.55
    ㄙ
    0.55
    гина
    0.53
    м
    0.49
     sarcoma
    0.47
    𒋢
    0.46
    ма
    0.45
    еха
    0.45
    ходе
    0.45
    器具
    0.45
    POSITIVE LOGITS
     frigor
    0.54
    장을
    0.53
     bestimm
    0.48
    ành
    0.47
     obligé
    0.46
    <unused598>
    0.44
     kürz
    0.44
    urile
    0.43
     ogran
    0.43
     nuova
    0.43
    Activations Density 0.000%

    No Known Activations