© 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. 197250
    Prev
    Next
    INDEX
    Explanations

    commenting on news and events

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

    generates and creates

    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
     ธ
    0.48
     जिसे
    0.48
     ㅎ
    0.47
     ਫ
    0.47
     уту
    0.46
     조건
    0.45
     숫자
    0.45
     な
    0.45
     Fallout
    0.45
     สา
    0.45
    POSITIVE LOGITS
     boxers
    0.51
     riport
    0.49
    قص
    0.47
    لوان
    0.45
     bearers
    0.45
    آور
    0.45
     identific
    0.45
     boxer
    0.44
    ালক
    0.44
     exchanged
    0.44
    Activations Density 0.001%

    No Known Activations