© 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. 31-GEMMASCOPE-2-RES-262K
    7. 100037
    Prev
    Next
    INDEX
    Explanations

    partnering with I

    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_31_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
     Athen
    0.56
    in
    0.52
    Than
    0.49
    䒽
    0.49
    at
    0.48
    lished
    0.47
    inguistic
    0.47
    çay
    0.47
    inou
    0.47
    us
    0.46
    POSITIVE LOGITS
     Ω
    0.48
    setBadge
    0.46
     उभार
    0.45
    에서도
    0.45
    是对
    0.43
     SLA
    0.42
     I
    0.40
    0.39
     spé
    0.39
    动作
    0.39
    Activations Density 0.002%

    No Known Activations