© 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. 38126
    Prev
    Next
    INDEX
    Explanations

    correcting names and numbers

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

    china

    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
    nlm
    0.39
     Prong
    0.39
     prong
    0.38
    PASS
    0.38
    Fraud
    0.38
    后悔
    0.38
    WHY
    0.38
    <u>
    0.38
     अभियांत्रिकी
    0.38
     fpr
    0.38
    POSITIVE LOGITS
     tratado
    0.52
     Translated
    0.51
     behand
    0.48
     novedad
    0.47
    ária
    0.46
     treatments
    0.45
    ése
    0.44
    rául
    0.43
    Translated
    0.43
     treated
    0.43
    Activations Density 0.001%

    No Known Activations