© 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. 221598
    Prev
    Next
    INDEX
    Explanations

    your new

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

    quoted strings

    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
     untreated
    0.44
     noxious
    0.43
     turt
    0.42
    faits
    0.42
     EU
    0.42
     flushed
    0.42
    ☐
    0.40
     fuelled
    0.40
    。
    0.40
     :/
    0.39
    POSITIVE LOGITS
     человеку
    0.55
    бал
    0.54
     ইমরান
    0.52
     इमरान
    0.52
     mannen
    0.48
     എഴു
    0.48
     Сол
    0.48
    쓱
    0.47
     elétrica
    0.46
     школе
    0.45
    Activations Density 0.000%

    No Known Activations