© 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. 138995
    Prev
    Next
    INDEX
    Explanations

    conditions attached

    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
     schrift
    0.52
     Stab
    0.48
     Leben
    0.46
     Leid
    0.46
     stuck
    0.46
     Griffith
    0.45
     zlo
    0.44
    嶅
    0.44
     quiet
    0.44
     still
    0.44
    POSITIVE LOGITS
    Incrementor
    0.46
    Recipes
    0.46
     дохода
    0.46
    masks
    0.46
     लौटे
    0.43
    bringing
    0.43
     underwriters
    0.43
     выпу
    0.42
     mutagenesis
    0.41
     সম্পদের
    0.41
    Activations Density 0.004%

    No Known Activations