© 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. 76628
    Prev
    Next
    INDEX
    Explanations

    This allows

    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
    찡
    0.48
     Diseño
    0.47
     oluştur
    0.46
     જ્યારે
    0.46
    Cré
    0.46
    Созда
    0.45
    ottesville
    0.44
     Київ
    0.44
     DEPEND
    0.44
    DEPEND
    0.43
    POSITIVE LOGITS
    (
    0.58
     infotainment
    0.43
     abrasive
    0.41
    ,(
    0.41
    ((
    0.40
     being
    0.39
     nilpotent
    0.39
     whirlwind
    0.38
    (["
    0.38
     purview
    0.38
    Activations Density 0.009%

    No Known Activations