© 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. 25127
    Prev
    Next
    INDEX
    Explanations

    rule, selling, Chartered

    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
     আবদ্ধ
    0.37
    讵
    0.37
    Device
    0.36
    Syntax
    0.35
    anjian
    0.35
    Schema
    0.34
    HttpMessage
    0.34
    ":
    0.34
    Lett
    0.34
    .}$
    0.33
    POSITIVE LOGITS
     clums
    0.37
     hoy
    0.37
     eles
    0.36
     stare
    0.36
     idag
    0.35
     aras
    0.34
     flaves
    0.34
     diri
    0.34
     vicinity
    0.34
     omkring
    0.34
    Activations Density 0.020%

    No Known Activations