© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 110892
    Prev
    Next
    INDEX
    Explanations

    no predictability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ignores
    0.42
    מית
    0.37
     Ignore
    0.36
    休憩
    0.36
    럿
    0.36
     ignored
    0.35
     влас
    0.35
    ｀)
    0.35
    NB
    0.35
    อย
    0.35
    POSITIVE LOGITS
     कक्क
    0.44
     xm
    0.41
    Qui
    0.39
    excel
    0.39
    wiz
    0.38
    ilm
    0.38
    sensing
    0.38
    🪁
    0.38
    osperm
    0.38
    QUI
    0.38
    Activations Density 0.000%

    No Known Activations