© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 27463
    Prev
    Next
    INDEX
    Explanations

    greetings from locations or origins

    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
    e
    0.55
    *$
    0.54
     unpredictable
    0.51
    ത്തുന്ന
    0.50
     pār
    0.49
     ಕಡಿಮೆ
    0.49
     selezione
    0.49
    tasks
    0.48
     Whom
    0.48
    beat
    0.47
    POSITIVE LOGITS
     कुंडली
    0.48
    .'
    0.45
    .');
    0.44
    వ్య
    0.44
    ليات
    0.43
    .):
    0.42
    لي
    0.42
     tyre
    0.41
     \
    0.40
    ^{'
    0.40
    Activations Density 0.000%

    No Known Activations