© 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. 75457
    Prev
    Next
    INDEX
    Explanations

    proper nouns and company names

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

    societal rejection, fertile patch

    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
    BlackRatingDiff
    0.47
    楶
    0.46
     सत्र
    0.45
    ए
    0.43
    Contrary
    0.42
    ິດຕ
    0.42
    èo
    0.41
    ➺
    0.41
     সঙ্গীত
    0.40
    Krishna
    0.40
    POSITIVE LOGITS
     suddiv
    0.45
     pengendalian
    0.44
     hectare
    0.43
    configuring
    0.43
     suda
    0.43
    uri
    0.42
    置き
    0.42
     Definitions
    0.42
     uy
    0.41
     facendo
    0.41
    Activations Density 0.001%

    No Known Activations