© 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. 138682
    Prev
    Next
    INDEX
    Explanations

    to defend

    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
     summons
    0.48
    iousness
    0.45
     toad
    0.45
    š
    0.45
     fermionic
    0.44
     torus
    0.43
     coups
    0.43
     toroidal
    0.43
     collapses
    0.43
    worldly
    0.42
    POSITIVE LOGITS
    ול
    0.46
     Investigative
    0.45
     kişi
    0.45
    rista
    0.44
     مزاح
    0.43
     Tuition
    0.43
    设计
    0.43
    淍
    0.43
     Anleitung
    0.42
    的感觉
    0.42
    Activations Density 0.005%

    No Known Activations