© 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. 28561
    Prev
    Next
    INDEX
    Explanations

    financial protection

    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
     الق
    0.44
    cours
    0.43
    ass
    0.42
     cerim
    0.42
    تر
    0.41
    増
    0.40
     كر
    0.40
    quisite
    0.38
     mdl
    0.38
    时刻
    0.38
    POSITIVE LOGITS
     SupCt
    0.51
     pabbaj
    0.50
    .??.??"]
    0.49
    KOV
    0.47
    舢
    0.46
     చేప
    0.46
     ෆ
    0.46
     inhomogeneities
    0.45
    אר
    0.45
     oysters
    0.45
    Activations Density 0.001%

    No Known Activations