© 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. 152267
    Prev
    Next
    INDEX
    Explanations

    led him to propose

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

    legal updates

    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
     U
    0.43
     Uranium
    0.43
     suspensión
    0.43
     IDENT
    0.42
     vot
    0.41
    ンス
    0.41
    riterien
    0.40
     L
    0.39
     fever
    0.39
     ಲ
    0.39
    POSITIVE LOGITS
     scholastic
    0.48
     רק
    0.47
    alanya
    0.44
    बित
    0.44
     bukanlah
    0.44
     ولی
    0.43
    perclip
    0.43
    Additive
    0.42
    ElementSibling
    0.41
    ת
    0.41
    Activations Density 0.000%

    No Known Activations