© 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. 111625
    Prev
    Next
    INDEX
    Explanations

    reception lobby

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

    languages and other languages

    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
    bian
    0.45
    ك
    0.45
    एक्स
    0.43
     victorious
    0.43
    तरे
    0.42
    꼴
    0.42
    ullary
    0.42
    يلا
    0.42
    বারে
    0.41
     moim
    0.40
    POSITIVE LOGITS
     prak
    0.48
     meetup
    0.48
     פאר
    0.47
     ਵਿਚ
    0.46
     สํา
    0.45
     trabaj
    0.45
     אר
    0.45
     poc
    0.45
    áról
    0.44
     포
    0.44
    Activations Density 0.000%

    No Known Activations