© 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. 109549
    Prev
    Next
    INDEX
    Explanations

    destroy results shall ended I very amazed pixels Register

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

    characteristics section

    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
    irm
    0.51
    𒊏
    0.49
     दृढ़
    0.48
     لون
    0.48
     নিশ্চিত
    0.47
    wen
    0.46
     مصنوع
    0.45
     القسم
    0.45
    iyy
    0.45
    াতিক
    0.45
    POSITIVE LOGITS
    ”
    0.48
    \"
    0.46
    ান্তি
    0.40
     Lydia
    0.40
     dormant
    0.40
    GISLATIVE
    0.39
     derr
    0.39
    PASS
    0.38
     Hawkins
    0.38
    CO
    0.38
    Activations Density 0.000%

    No Known Activations