© 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. 16-GEMMASCOPE-2-RES-262K
    7. 11414
    Prev
    Next
    INDEX
    Explanations

    Dr. title

    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_16_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
    UCH
    0.82
    RIC
    0.77
     resell
    0.75
    태
    0.75
    TION
    0.74
     airfield
    0.74
     criticize
    0.74
     올
    0.73
     لوبوي
    0.73
    TANK
    0.73
    POSITIVE LOGITS
    ة
    1.52
    ك
    1.49
    ing
    1.45
    ה
    1.41
    a
    1.29
    ه
    1.28
    ن
    1.23
    ı
    1.20
     Dr
    1.17
    st
    1.16
    Activations Density 0.002%

    No Known Activations