© 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-65K
    7. 4877
    Prev
    Next
    INDEX
    Explanations

    splitting creates

    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_65k_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
    O
    0.56
    as
    0.52
    only
    0.51
    Pacific
    0.51
    an
    0.48
    Acting
    0.48
    Gm
    0.48
    Only
    0.47
    G
    0.47
    Ocean
    0.47
    POSITIVE LOGITS
    icata
    0.47
    সিস
    0.45
     లో
    0.45
     হ
    0.44
     railings
    0.42
     питания
    0.42
     ሁ
    0.41
     పుష్
    0.41
     railing
    0.41
    技术的
    0.41
    Activations Density 0.005%

    No Known Activations