© 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. 32165
    Prev
    Next
    INDEX
    Explanations

    vegetarian, act, mainstay, community

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

    explanation and understanding

    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
    be
    0.48
    dec
    0.48
    बु
    0.46
     \|_{
    0.46
    meleri
    0.45
     jugs
    0.44
    အ
    0.44
    滁
    0.43
    fj
    0.43
    부에
    0.43
    POSITIVE LOGITS
     необ
    0.47
    ી
    0.46
    FindingsResponse
    0.46
    LOTRE
    0.45
    ﻮ
    0.44
    贤
    0.43
    oulou
    0.43
    ם
    0.43
     trac
    0.43
    த்தைப்
    0.42
    Activations Density 0.000%

    No Known Activations