© 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. 84467
    Prev
    Next
    INDEX
    Explanations

    investigation and detective agencies

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

    acknowledges why

    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
    ेज
    0.46
    СТ
    0.42
     搭
    0.42
    নের
    0.42
     solit
    0.42
    нную
    0.42
    슷
    0.42
    olem
    0.41
    retta
    0.40
    ໍ່
    0.39
    POSITIVE LOGITS
     authority
    0.56
     Woman
    0.52
     facility
    0.52
     radius
    0.50
     Authority
    0.50
    Ž
    0.49
     dicen
    0.48
     Event
    0.48
     Microphone
    0.48
     Women
    0.48
    Activations Density 0.000%

    No Known Activations