© 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. 14117
    Prev
    Next
    INDEX
    Explanations

    less direct, not always single

    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
    Ket
    0.45
    这款
    0.42
    Pa
    0.42
    K
    0.42
    DbContext
    0.41
    Widget
    0.40
    Dense
    0.40
    Gl
    0.40
    FundMe
    0.39
    lattice
    0.38
    POSITIVE LOGITS
     affective
    0.44
    旪
    0.43
     essentiel
    0.42
     organizer
    0.42
     distin
    0.40
     condensers
    0.40
    ineux
    0.40
     smaller
    0.40
     identified
    0.40
     unique
    0.39
    Activations Density 0.005%

    No Known Activations