© 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. 116021
    Prev
    Next
    INDEX
    Explanations

    perfect square factors

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

    safety, potential, celebration

    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
    ある
    0.47
     =
    0.47
     উচিত
    0.47
     voraus
    0.47
    říklad
    0.46
    ؟
    0.46
    ಋ
    0.44
     лето
    0.43
    Warum
    0.43
    械
    0.43
    POSITIVE LOGITS
    bés
    0.46
     aço
    0.46
     evacu
    0.45
     cloths
    0.44
    meln
    0.44
    ලු
    0.44
    serialize
    0.44
     experiências
    0.43
    fromi
    0.43
    전
    0.43
    Activations Density 0.001%

    No Known Activations