© 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. 125892
    Prev
    Next
    INDEX
    Explanations

    foreign language text

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

    mythological names and spin states

    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
    ad
    0.54
    er
    0.53
    ure
    0.49
    ws
    0.46
    hid
    0.45
    osa
    0.45
    vre
    0.44
    p
    0.44
    ar
    0.43
    i
    0.43
    POSITIVE LOGITS
    ни
    0.56
    נ
    0.55
    Пе
    0.55
    كال
    0.54
    እንደ
    0.54
    ፔ
    0.54
     አስፈላጊ
    0.53
     कामयाबी
    0.53
    잘
    0.53
     градусов
    0.52
    Activations Density 0.000%

    No Known Activations