© 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. 39969
    Prev
    Next
    INDEX
    Explanations

    adding elements to end

    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
     Simult
    0.42
    Comprehensive
    0.41
    贍
    0.41
    porcion
    0.40
    $-
    0.40
     शोर
    0.40
     আর্জেন্টিনা
    0.39
     സർക്കാർ
    0.39
     కార్యక్ర
    0.39
    司法
    0.39
    POSITIVE LOGITS
     existing
    0.50
    existing
    0.46
     Existing
    0.42
     insertion
    0.41
     늘
    0.39
     inserting
    0.38
     기존
    0.38
     overcoming
    0.37
     insert
    0.36
     ride
    0.36
    Activations Density 0.039%

    No Known Activations