© 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. 33395
    Prev
    Next
    INDEX
    Explanations

    stories about others

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

    embedding

    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
     शेष
    0.52
    تاء
    0.52
    र
    0.51
    тила
    0.50
    р
    0.49
    電源
    0.47
    рты
    0.45
    মতী
    0.45
    вать
    0.45
    wheels
    0.45
    POSITIVE LOGITS
     był
    0.49
     campione
    0.48
     famiglia
    0.48
    iamo
    0.46
     intorno
    0.46
     supre
    0.44
     שמ
    0.44
     ಅಭಿ
    0.44
     وزی
    0.44
    蒾
    0.44
    Activations Density 0.000%

    No Known Activations