© 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. 240760
    Prev
    Next
    INDEX
    Explanations

    video titles and questions

    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
    傥
    0.43
     где
    0.43
     happens
    0.43
    枤
    0.42
     investasi
    0.41
    鲁
    0.40
    酱
    0.40
    тальян
    0.40
    峣
    0.40
     aconteceu
    0.39
    POSITIVE LOGITS
     Archbishop
    0.42
    criptor
    0.42
    neg
    0.41
    evan
    0.41
    ভোকেট
    0.41
    $_{
    0.40
    illes
    0.40
    yne
    0.40
     ஆகியோர்
    0.39
    izons
    0.39
    Activations Density 0.001%

    No Known Activations