© 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. 28491
    Prev
    Next
    INDEX
    Explanations

    emphasis and qualification

    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
    ኾ
    0.50
    ДА
    0.48
    GameObject
    0.47
    IONS
    0.47
    IsOpen
    0.47
    ндары
    0.46
    璺
    0.46
    зіно
    0.46
    IsPass
    0.46
    AssetDiscovery
    0.46
    POSITIVE LOGITS
     easier
    0.75
     able
    0.71
     an
    0.69
     akin
    0.68
     on
    0.64
     a
    0.63
     portrayed
    0.63
     not
    0.60
     plagued
    0.60
     una
    0.59
    Activations Density 0.128%

    No Known Activations