© 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. 202457
    Prev
    Next
    INDEX
    Explanations

    check off

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

    labels and classifications

    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
    Champions
    0.47
    ussi
    0.46
    built
    0.46
    プログラム
    0.45
     ಮಕ್ಕಳ
    0.44
    SPL
    0.43
     Built
    0.43
    펄
    0.43
     Champions
    0.43
    from
    0.42
    POSITIVE LOGITS
     :).
    0.52
     }.
    0.49
     adduced
    0.49
     Gos
    0.47
     :(
    0.47
     Barbar
    0.45
     الدي
    0.45
    tela
    0.45
     Akhtar
    0.45
     }
    0.44
    Activations Density 0.001%

    No Known Activations