© 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. 4266
    Prev
    Next
    INDEX
    Explanations

    celebrating

    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
    ל
    1.30
    ल
    1.20
    N
    1.19
    ل
    1.13
    この
    1.05
    ור
    1.01
    ă
    1.00
    很
    0.96
    おそらく
    0.95
    SC
    0.95
    POSITIVE LOGITS
    in
    1.12
    지
    1.07
    t
    1.02
     not
    0.99
    تي
    0.89
    ین
    0.88
    <0x0D>
    0.86
    inni
    0.86
    0
    0.86
    ار
    0.85
    Activations Density 0.010%

    No Known Activations