© 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. 119411
    Prev
    Next
    INDEX
    Explanations

    unfinished content or labels

    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
    ads
    0.38
     Pose
    0.38
     출
    0.38
     ติด
    0.37
    বেই
    0.37
     mirror
    0.37
     mirroring
    0.37
     moim
    0.37
    ach
    0.36
    uir
    0.36
    POSITIVE LOGITS
     eos
    0.41
    pager
    0.41
     incomple
    0.40
    لې
    0.39
    idity
    0.38
    䣼
    0.38
    unfinished
    0.38
     gminy
    0.38
    Transit
    0.37
    ︿
    0.37
    Activations Density 0.000%

    No Known Activations