© 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. 111416
    Prev
    Next
    INDEX
    Explanations

    lists separated by commas

    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
    <0xC2>
    0.44
    礼
    0.38
    ្ស
    0.37
    胿
    0.36
     cả
    0.36
    ເນ
    0.36
     occasionally
    0.35
     combination
    0.35
     соответствует
    0.35
    гъ
    0.35
    POSITIVE LOGITS
    adin
    0.40
    aniye
    0.37
     कोणता
    0.37
    rijf
    0.36
    igens
    0.36
    Wage
    0.35
    culis
    0.34
    鲶
    0.34
    loadNpm
    0.34
    avier
    0.34
    Activations Density 0.040%

    No Known Activations