© 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. 3688
    Prev
    Next
    INDEX
    Explanations

    outstanding achievement or performance

    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
     môže
    1.14
    دي
    1.09
     in
    1.05
     ي
    1.04
    р
    1.00
     maar
    0.98
    $$
    0.97
    ني
    0.97
     الذي
    0.97
    스
    0.97
    POSITIVE LOGITS
    ue
    1.36
    یم
    1.30
    outstanding
    1.24
    .
    1.23
    il
    1.13
     ذریع
    1.12
    पणे
    1.08
    om
    1.06
    iv
    1.05
    ach
    1.05
    Activations Density 0.001%

    No Known Activations