© 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. 233361
    Prev
    Next
    INDEX
    Explanations

    features listed after 'include' or 'of'

    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
    ১৭
    0.60
    К
    0.55
     корпуса
    0.54
     слоя
    0.51
     можа
    0.51
    밴
    0.51
    紊
    0.51
     интегри
    0.50
    綃
    0.49
     тыся
    0.49
    POSITIVE LOGITS
     peanut
    0.45
     vaccine
    0.44
    :
    0.43
     pause
    0.42
     disadvantaged
    0.41
    പ്പിച്ചി
    0.41
     mengh
    0.41
    sta
    0.41
    oken
    0.40
    ugging
    0.40
    Activations Density 0.000%

    No Known Activations