© 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. 31886
    Prev
    Next
    INDEX
    Explanations

    not in

    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
    GT
    0.38
    オリ
    0.37
     tep
    0.36
    向け
    0.36
    ور
    0.35
    สร
    0.35
    添
    0.35
     აღმასრულ
    0.34
     apuesta
    0.34
    U
    0.34
    POSITIVE LOGITS
    不在
    0.56
    notin
    0.48
     none
    0.47
     outside
    0.46
     neither
    0.45
     within
    0.44
     unchanged
    0.44
     None
    0.44
     hiçbir
    0.43
     unforeseen
    0.43
    Activations Density 0.012%

    No Known Activations