© 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. 14383
    Prev
    Next
    INDEX
    Explanations

    bullet points

    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
    ル
    1.42
    로
    1.42
    ل
    1.41
    も
    1.19
    л
    1.13
    もら
    1.10
    اتی
    1.09
    لای
    1.09
     در
    1.08
    대
    1.07
    POSITIVE LOGITS
     bullet
    1.30
     Bullet
    1.20
    Bullet
    1.15
    bullet
    1.13
     bullets
    0.98
    3
    0.91
    لي
    0.89
    O
    0.89
    at
    0.86
    <0x0D>
    0.84
    Activations Density 0.006%

    No Known Activations