© 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. 100928
    Prev
    Next
    INDEX
    Explanations

    numbers and specific items

    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
    オル
    0.48
    閎
    0.47
    shund
    0.46
     ditth
    0.46
    之人
    0.45
     оде
    0.44
     ふ
    0.44
    弟子
    0.43
    othor
    0.43
    Rq
    0.43
    POSITIVE LOGITS
    čiai
    0.37
     Acceptance
    0.37
    ↵↵
    0.36
    armament
    0.36
    тков
    0.36
    ↵↵↵
    0.35
     Dynamical
    0.35
    ωσης
    0.35
     Guns
    0.34
     Tru
    0.34
    Activations Density 0.003%

    No Known Activations