© 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. 109863
    Prev
    Next
    INDEX
    Explanations

    how we think and process

    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
     b
    0.45
     CRISPR
    0.43
     sp
    0.43
    ного
    0.43
    ный
    0.42
    ?
    0.41
     m
    0.40
     grew
    0.40
    ώρα
    0.40
     technology
    0.40
    POSITIVE LOGITS
     தேர்தலில்
    0.52
    
    0.52
     формате
    0.50
    amaya
    0.49
     Applicable
    0.48
    ینگ
    0.48
     کیونکہ
    0.47
     ತೆಗೆದುಕೊಳ್ಳ
    0.47
     Гинд
    0.47
     ಸುಬ್ಬ
    0.47
    Activations Density 0.000%

    No Known Activations