© 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. 77369
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    markdown code blocks

    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
     ulcer
    0.48
    anson
    0.46
     पशु
    0.44
    lessness
    0.43
    ت
    0.43
     سرعت
    0.43
    는
    0.43
    resonant
    0.42
    smt
    0.42
    }_{[
    0.42
    POSITIVE LOGITS
    oną
    0.52
     già
    0.52
    اي
    0.50
     uno
    0.50
     Selfie
    0.49
     Gaff
    0.49
    ্রো
    0.48
    ஸ்தான
    0.48
     Nick
    0.48
    প্রণ
    0.47
    Activations Density 0.000%

    No Known Activations