© 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. 235857
    Prev
    Next
    INDEX
    Explanations

    stations, patents, careers, when

    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
     খাব
    0.47
     vec
    0.46
     hő
    0.45
    r
    0.45
    চ্চ
    0.45
     Begriff
    0.45
     burgl
    0.44
    జ్ఞ
    0.44
    蝮
    0.44
    龜
    0.43
    POSITIVE LOGITS
    सभी
    0.53
     স্টেট
    0.51
     выполнен
    0.49
    essions
    0.48
    ssa
    0.48
     введен
    0.48
     желательно
    0.47
    पीएससी
    0.46
     ауди
    0.46
    kates
    0.45
    Activations Density 0.001%

    No Known Activations