© 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. 217207
    Prev
    Next
    INDEX
    Explanations

    phrases starting with common words

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

    Business context conclusions

    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
    л
    0.54
    hos
    0.47
    ל
    0.46
    NaN
    0.46
    ulfide
    0.45
    rato
    0.44
    றிவு
    0.44
    roc
    0.43
    hi
    0.42
     హిట్
    0.42
    POSITIVE LOGITS
    。
    0.53
    ◑
    0.51
    。『
    0.50
     طریق
    0.49
    .).
    0.48
     Auer
    0.47
    ھا
    0.47
     系统
    0.46
     Endocrinol
    0.46
    กับการ
    0.46
    Activations Density 0.000%

    No Known Activations