© 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. 237882
    Prev
    Next
    INDEX
    Explanations

    depending on; characterized by; people who

    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
    まったく
    0.51
     विवेक
    0.50
    air
    0.50
    dynamic
    0.50
    ai
    0.49
    全く
    0.49
     アメリカ
    0.49
    ก
    0.48
    ки
    0.47
    いや
    0.47
    POSITIVE LOGITS
    ائح
    0.48
    였습니다
    0.46
    ន្ទ
    0.45
    ocytic
    0.44
    ِح
    0.43
     tabBar
    0.43
    Entonces
    0.43
     ticked
    0.42
    তখন
    0.42
    地板
    0.41
    Activations Density 0.000%

    No Known Activations