© 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. 185781
    Prev
    Next
    INDEX
    Explanations

    Epub, cluster, degree, package, rainbow

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

    Natural Language Processing (NLP)

    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
     bcrypt
    0.50
    கிறது
    0.48
     acrobat
    0.47
    免許
    0.46
    ቂ
    0.46
    휙
    0.45
     bruit
    0.44
     pracy
    0.44
    ᙱ
    0.44
     brillo
    0.44
    POSITIVE LOGITS
    peria
    0.46
    residents
    0.46
    leveland
    0.44
    pera
    0.44
    Anch
    0.44
    Purch
    0.44
    াস্ট
    0.43
    Lo
    0.43
    Residents
    0.42
    Pub
    0.42
    Activations Density 0.000%

    No Known Activations