© 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. 134649
    Prev
    Next
    INDEX
    Explanations

    distance or position

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

    first contact and meeting

    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
     Diseño
    0.52
    英國
    0.46
    Ⅳ
    0.46
     Vote
    0.46
     Entretanto
    0.45
    指导
    0.45
    лма
    0.44
     explicado
    0.44
     Μα
    0.43
     DR
    0.43
    POSITIVE LOGITS
     seem
    0.51
     vajj
    0.50
    چھے
    0.49
    ček
    0.47
    feier
    0.46
    墂
    0.46
    urek
    0.46
    یں۔
    0.45
    formatics
    0.45
    याँ
    0.44
    Activations Density 0.000%

    No Known Activations