© 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. 150285
    Prev
    Next
    INDEX
    Explanations

    very comfortable

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

    tense conversations

    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
     preimage
    0.47
    า
    0.47
    onent
    0.47
     आंतरिक
    0.47
     പരിശോധ
    0.46
     എന്നാൽ
    0.46
     );
    0.45
    ）；
    0.45
    ้ำ
    0.44
    mē
    0.44
    POSITIVE LOGITS
    пол
    0.50
    SCHOOL
    0.49
    зора
    0.48
    "
    0.48
    рожден
    0.46
    학교
    0.45
    مان
    0.45
    шина
    0.44
    зо
    0.44
    ходи
    0.43
    Activations Density 0.000%

    No Known Activations