© 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. 249310
    Prev
    Next
    INDEX
    Explanations

    wine, pharmacy, travel, image

    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
     प्रवाह
    0.48
     ል
    0.48
    ادث
    0.48
    稟
    0.47
    券
    0.46
    ビア
    0.45
     μέσω
    0.44
     صل
    0.44
    ジネス
    0.43
    買取
    0.43
    POSITIVE LOGITS
    v
    0.69
    to
    0.68
    h
    0.68
    p
    0.68
    b
    0.68
    t
    0.67
    us
    0.60
    s
    0.60
    c
    0.58
    i
    0.56
    Activations Density 0.001%

    No Known Activations