© 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. 6924
    Prev
    Next
    INDEX
    Explanations

    introduces exceptions unless

    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
    to
    1.72
    p
    1.47
    a
    1.46
    1.38
     was
    1.34
    ية
    1.30
    z
    1.28
    the
    1.25
    و
    1.21
    c
    1.20
    POSITIVE LOGITS
    ح
    1.30
    ς
    1.17
    adır
    1.14
    ↵
    1.09
    스
    1.09
    aculture
    1.06
    5
    1.06
    기
    1.05
    იდ
    1.04
    기와
    1.03
    Activations Density 0.005%

    No Known Activations