© 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. 46577
    Prev
    Next
    INDEX
    Explanations

    Mistral 7B

    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
    า
    0.76
    0
    0.60
    স
    0.60
    ח
    0.58
    But
    0.57
    They
    0.57
          
    0.56
     Parton
    0.56
     Oil
    0.55
    The
    0.54
    POSITIVE LOGITS
    ﮈ
    0.60
     malas
    0.55
     appellees
    0.53
     dislocations
    0.53
     bords
    0.52
     orthodontic
    0.52
     الاتحاد
    0.52
     двох
    0.52
     vestiges
    0.52
     inflation
    0.51
    Activations Density 0.004%

    No Known Activations