© 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. 41312
    Prev
    Next
    INDEX
    Explanations

    represented objects

    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
    exception
    0.53
    וג
    0.53
    lovers
    0.52
    א
    0.52
    uba
    0.51
    ao
    0.50
    limited
    0.50
    affine
    0.50
    sunline
    0.49
    any
    0.49
    POSITIVE LOGITS
     hikes
    0.50
     characters
    0.49
    在
    0.49
     domestically
    0.48
     personaggi
    0.48
     gli
    0.48
     retails
    0.47
     facing
    0.47
    这
    0.47
     Laboratories
    0.47
    Activations Density 0.000%

    No Known Activations