© 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. 12811
    Prev
    Next
    INDEX
    Explanations

    thank you for asking

    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
    Atlanta
    0.40
     Atlanta
    0.39
    ″
    0.39
    ”।
    0.39
    ।
    0.38
     Pittsburgh
    0.38
    ।-
    0.38
     Cincinnati
    0.38
     MGM
    0.37
    Pittsburgh
    0.37
    POSITIVE LOGITS
    }}^{*}\
    0.36
    畔
    0.35
    ános
    0.35
    利益
    0.34
     ""}
    0.34
     Fragen
    0.34
    赠
    0.34
     bertanya
    0.34
    to
    0.33
     amulet
    0.33
    Activations Density 0.002%

    No Known Activations