© 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. 61217
    Prev
    Next
    INDEX
    Explanations

    start of list item

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

    transactional systems or reports

    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
     verifica
    0.53
     peč
    0.50
    addassa
    0.46
     उत्तीर्ण
    0.46
     сестра
    0.46
    輯
    0.46
    ješ
    0.46
     நடைபெ
    0.45
     देम
    0.45
     Grö
    0.45
    POSITIVE LOGITS
    NT
    0.53
    i
    0.50
    COT
    0.48
    ONI
    0.47
    Dave
    0.47
    Tap
    0.46
    Scot
    0.46
    INN
    0.46
    ISION
    0.46
    तना
    0.45
    Activations Density 0.001%

    No Known Activations