© 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. 225497
    Prev
    Next
    INDEX
    Explanations

    admissionorbid

    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
    тивний
    0.46
    บ
    0.45
     beiden
    0.44
    outen
    0.44
    rard
    0.44
     शिवा
    0.43
     двумя
    0.42
     Wiz
    0.42
     Василь
    0.42
     двох
    0.42
    POSITIVE LOGITS
    လည်း
    0.48
    ='+
    0.47
    í
    0.45
    posaż
    0.45
    ţ
    0.44
    ząc
    0.43
    ț
    0.43
    纪
    0.43
    Ք
    0.43
    内心
    0.42
    Activations Density 0.001%

    No Known Activations