© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122900
    Prev
    Next
    INDEX
    Explanations

    cannot facilitate harmful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ꜰ
    0.41
    ໂດ
    0.41
    涵盖
    0.41
     ג
    0.40
    λέ
    0.39
    >∕
    0.39
    enaries
    0.38
     motionProxy
    0.38
    驱
    0.38
    大部分
    0.38
    POSITIVE LOGITS
    などが
    0.39
     exista
    0.37
     supposing
    0.37
     ہوں۔
    0.37
     harmless
    0.36
     Immobilien
    0.36
     are
    0.35
     potrà
    0.35
     potrebbero
    0.35
     sweetheart
    0.34
    Activations Density 0.002%

    No Known Activations