© 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. 178877
    Prev
    Next
    INDEX
    Explanations

    signing checks, RTI Act, really liked, really hope, 4 registration

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

    Adolf Hitler, state-sponsored atrocities

    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
    コ
    0.49
    ativ
    0.49
    со
    0.48
     passiert
    0.48
     rice
    0.48
    ات
    0.48
     マルチ
    0.48
     レ
    0.47
     lavor
    0.47
    ز
    0.47
    POSITIVE LOGITS
     Callum
    0.50
     специфи
    0.47
     Виктор
    0.46
     intrinsic
    0.45
     nhằm
    0.45
    극한
    0.44
     покрытие
    0.44
     мебели
    0.43
     intentions
    0.42
     одежды
    0.41
    Activations Density 0.001%

    No Known Activations