© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151660
    Prev
    Next
    INDEX
    Explanations

    designed specifically

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

    organizational behavior and official contexts

    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
    ト
    0.48
    Д
    0.46
    RL
    0.45
    াইট
    0.43
    its
    0.43
     പറയുന്നത്
    0.43
    laut
    0.43
    ТО
    0.43
    К
    0.43
    ܩ
    0.42
    POSITIVE LOGITS
     gacche
    0.48
     trauma
    0.47
     HttpException
    0.47
     পাশ্চ
    0.46
     Textile
    0.46
     Textiles
    0.45
    觑
    0.45
     industrie
    0.44
     Secrets
    0.44
     flexion
    0.44
    Activations Density 0.000%

    No Known Activations