© 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. 21519
    Prev
    Next
    INDEX
    Explanations

    no longer, the animal, all different

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

    example targets

    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
     계약
    0.35
     രാഷ്ട്രീയ
    0.31
    ަ
    0.31
     полити
    0.31
    เว็บไซต์
    0.31
     contrato
    0.30
     കരാ
    0.30
    wikidata
    0.30
     Қ
    0.29
    businessman
    0.29
    POSITIVE LOGITS
     adsorbed
    0.36
     nonzero
    0.36
     over
    0.34
     using
    0.34
     reduziert
    0.33
     reduce
    0.32
    +.
    0.32
     usamos
    0.32
     addirittura
    0.32
     wirelessly
    0.32
    Activations Density 0.000%

    No Known Activations