© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15585
    Prev
    Next
    INDEX
    Explanations

    html doctype

    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_40_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
    lə
    0.45
    FOL
    0.44
     подой
    0.42
    lendir
    0.42
    acelet
    0.41
    lari
    0.40
    <unused1079>
    0.40
    에게
    0.40
    RAIT
    0.39
    uleiro
    0.39
    POSITIVE LOGITS
     LOCKED
    0.41
     locks
    0.41
     neutralize
    0.40
     species
    0.40
    syntax
    0.40
    imens
    0.39
    pannt
    0.39
     locked
    0.38
    ز
    0.38
     VHS
    0.38
    Activations Density 0.001%

    No Known Activations