© 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. 579
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by punctuation or short strings

    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
     a
    1.41
    (
    1.30
     I
    1.21
     that
    1.01
    that
    0.96
    l
    0.95
    ning
    0.91
    -
    0.91
     C
    0.84
    stit
    0.83
    POSITIVE LOGITS
    ו
    1.47
    ח
    1.17
    ج
    1.03
    ש
    1.02
    س
    1.01
    و
    0.98
    ه
    0.97
    ف
    0.94
     луч
    0.93
    на
    0.93
    Activations Density 0.200%

    No Known Activations