© 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. 17723
    Prev
    Next
    INDEX
    Explanations

    questions and suggestions

    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
    IS
    1.25
    Y
    1.15
    J
    1.13
    O
    1.13
    ed
    1.09
    ش
    1.08
    ४
    1.08
    al
    1.05
    US
    1.05
    <unused2172>
    1.05
    POSITIVE LOGITS
    ні
    1.26
    ู
    1.11
    ↵
    1.03
    :
    1.00
    in
    0.96
     quart
    0.96
    ர்
    0.96
     summar
    0.95
    -
    0.95
    ه
    0.95
    Activations Density 0.000%

    No Known Activations