© 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. 19001
    Prev
    Next
    INDEX
    Explanations

    nearby locations and best information

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

    starting with

    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
     Biotechnol
    0.46
     Dalib
    0.42
    стами
    0.42
    acetamol
    0.41
    发现
    0.41
    acin
    0.40
    -.
    0.40
    স্‌
    0.40
    snapshot
    0.40
     aktywn
    0.40
    POSITIVE LOGITS
     срок
    0.46
     dogma
    0.44
     merit
    0.43
     го
    0.43
     lame
    0.43
     срока
    0.43
     планы
    0.42
     ね
    0.42
    ہے
    0.41
     את
    0.41
    Activations Density 0.000%

    No Known Activations