© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154741
    Prev
    Next
    INDEX
    Explanations

    job application

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

    loading datasets and models

    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
    NameTo
    0.49
    ئه
    0.49
    дія
    0.48
    েই
    0.46
    ায়ে
    0.46
    纓
    0.45
    ляем
    0.45
    氏
    0.45
    ษัท
    0.44
    োয়া
    0.44
    POSITIVE LOGITS
    uv
    0.53
    no
    0.50
    pOt
    0.49
    ula
    0.47
    p
    0.47
     BACH
    0.46
     sinusoidal
    0.45
    bpm
    0.45
    wis
    0.44
     contenders
    0.44
    Activations Density 0.000%

    No Known Activations