© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    technical components and specifications

    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
     sogenannten
    0.44
    ੧
    0.44
     grammatical
    0.42
    któ
    0.42
    <unused968>
    0.42
     문제를
    0.40
    燐
    0.40
     ignor
    0.40
    <unused675>
    0.40
    感情
    0.39
    POSITIVE LOGITS
     +
    0.56
     vs
    0.52
    /
    0.52
     (
    0.51
     &
    0.48
     /
    0.48
    +
    0.44
     with
    0.43
     Residence
    0.41
     ((
    0.40
    Activations Density 0.148%

    No Known Activations