© 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. 7837
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT statements

    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
    ჯგუფი
    0.46
    氳
    0.42
    itäten
    0.41
    𝟰
    0.41
    晞
    0.41
    仴
    0.40
    chromiumfx
    0.40
     klanten
    0.40
    ബരിമല
    0.40
    
    0.40
    POSITIVE LOGITS
    enco
    0.46
    d
    0.43
     question
    0.42
     profile
    0.42
    all
    0.42
    find
    0.42
    unic
    0.42
    el
    0.41
     all
    0.41
     mul
    0.41
    Activations Density 0.000%

    No Known Activations