© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109880
    Prev
    Next
    INDEX
    Explanations

    "which" followed by descriptive verbs

    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_16_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
    مت
    0.88
    It
    0.70
    na
    0.70
     a
    0.67
    مة
    0.66
    م
    0.66
    de
    0.65
    tan
    0.64
    Suppose
    0.64
     It
    0.64
    POSITIVE LOGITS
    ান
    0.71
    '
    0.71
    chester
    0.66
    MAIL
    0.66
    '])->
    0.66
     เตรียม
    0.65
     胸
    0.64
     får
    0.63
    educated
    0.63
     แนะ
    0.63
    Activations Density 0.000%

    No Known Activations