© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135146
    Prev
    Next
    INDEX
    Explanations

    possible, necessary, or agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     used
    0.50
    from
    0.50
    al
    0.48
    scalar
    0.46
    Used
    0.45
    <start_of_image>
    0.45
    Ni
    0.44
     SCIENCE
    0.44
    NONE
    0.43
    Am
    0.43
    POSITIVE LOGITS
     possíveis
    0.52
     mögliche
    0.49
    χής
    0.48
     مدينه
    0.48
     वेरी
    0.47
    ător
    0.47
     verpflicht
    0.46
    kých
    0.45
     المد
    0.45
    妸
    0.44
    Activations Density 0.009%

    No Known Activations