© 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. 3285
    Prev
    Next
    INDEX
    Explanations

    tokens after certain words

    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
    ong
    0.50
    st
    0.50
    b
    0.48
     it
    0.48
    mo
    0.47
    nf
    0.47
    ing
    0.47
    lo
    0.47
    j
    0.46
    sun
    0.46
    POSITIVE LOGITS
    一台
    0.58
    的话
    0.49
    ดัง
    0.49
    สำคัญ
    0.47
    étaire
    0.46
     कॉनक
    0.45
    บริษัท
    0.44
    軗
    0.44
    েম্বর
    0.43
    话题
    0.43
    Activations Density 19.402%

    No Known Activations