© 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. 76330
    Prev
    Next
    INDEX
    Explanations

    assures that, section of, yours for

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

    prompts with specific endings

    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
    alous
    0.56
    e
    0.55
    ans
    0.48
    anner
    0.47
    otes
    0.47
    ued
    0.47
    し
    0.46
    ｅ
    0.45
    ible
    0.45
    ic
    0.45
    POSITIVE LOGITS
     фаразы
    0.50
     ?-
    0.50
     CheckKey
    0.50
     сохран
    0.46
     ফি
    0.45
     ?"
    0.45
    tım
    0.45
     "????.??.??"]
    0.45
     gu
    0.44
     проверка
    0.43
    Activations Density 0.001%

    No Known Activations