© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56814
    Prev
    Next
    INDEX
    Explanations

    buy my home

    np_acts-logits-general · gemini-2.5-flash-lite

    brand awareness, chatbot, reverse image search, violin, boundary, bread, answer key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cabrio
    0.44
     MBP
    0.43
     Hadoop
    0.40
    >,
    0.39
     Colorado
    0.39
     CZ
    0.38
     Fifty
    0.38
     Huddersfield
    0.38
    SSD
    0.38
     Camaro
    0.38
    POSITIVE LOGITS
    グ
    0.37
     pathophysiology
    0.37
    örg
    0.34
    防災
    0.34
    ลำ
    0.34
    രുത്
    0.34
     político
    0.34
     exerting
    0.34
    निर्भर
    0.34
    updateOne
    0.33
    Activations Density 0.036%

    No Known Activations