© 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. 200286
    Prev
    Next
    INDEX
    Explanations

    certain conditional outcomes

    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
    س
    0.53
     impairments
    0.45
    פ
    0.45
    وک
    0.45
     summarised
    0.44
    ገለ
    0.44
    י
    0.43
    ש
    0.43
     khuẩn
    0.43
     cures
    0.42
    POSITIVE LOGITS
     Thunderbird
    0.48
     vele
    0.47
     Ged
    0.46
    velope
    0.45
    zentration
    0.45
     technische
    0.45
    ний
    0.45
     технических
    0.44
     bey
    0.44
     භ
    0.44
    Activations Density 0.005%

    No Known Activations