© 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. 143913
    Prev
    Next
    INDEX
    Explanations

    vanished, leave, saved, invisible

    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
     aujourd
    0.43
    <em>
    0.41
     India
    0.41
    tern
    0.40
    geries
    0.40
     sitcom
    0.39
    oun
    0.39
    achelorette
    0.38
     कार्यक्रम
    0.38
    ég
    0.38
    POSITIVE LOGITS
    䥑
    0.43
    रा
    0.42
     অত্যা
    0.41
    醎
    0.41
    ３
    0.40
    Benzyloxy
    0.40
    豉
    0.39
    兟
    0.39
     сервера
    0.39
    苙
    0.39
    Activations Density 0.001%

    No Known Activations