© 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. 24200
    Prev
    Next
    INDEX
    Explanations

    only, false, not

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

    printing program output

    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
     METHODS
    0.42
    🎬
    0.41
     INDUSTRY
    0.39
     松
    0.37
     ALLO
    0.37
     OUTPUT
    0.37
     然後
    0.37
    Fitting
    0.37
    METHODS
    0.37
     HUAWEI
    0.36
    POSITIVE LOGITS
     sadece
    0.46
    都不是
    0.42
    걍
    0.42
     herhangi
    0.41
     نہیں۔
    0.41
     ninguno
    0.40
     hanya
    0.40
    false
    0.40
     רק
    0.39
     Bukan
    0.39
    Activations Density 0.002%

    No Known Activations