© 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. 49936
    Prev
    Next
    INDEX
    Explanations

    to [verb] or [noun]

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

    foreign conditional words

    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
     स्नात
    0.44
    lusconi
    0.43
    亟
    0.43
    netic
    0.43
     Aktien
    0.43
    ≾
    0.43
    meleri
    0.43
     अतुल
    0.43
     comedians
    0.42
    nicht
    0.42
    POSITIVE LOGITS
    決め
    0.55
     ل
    0.52
    季節
    0.48
     якщо
    0.47
     یا
    0.46
    InputDialog
    0.46
    判断
    0.45
     dacă
    0.44
     waarbij
    0.44
     ون
    0.44
    Activations Density 0.000%

    No Known Activations