© 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. 88802
    Prev
    Next
    INDEX
    Explanations

    produced negative

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

    historical or informational context

    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
    崩溃
    0.45
     =>
    0.45
     انہوں
    0.44
    I
    0.44
    Options
    0.43
    Utilization
    0.43
    咱们
    0.43
    J
    0.43
    副
    0.43
    Env
    0.42
    POSITIVE LOGITS
    риал
    0.52
    ҳ
    0.50
     જો
    0.48
    ড়
    0.47
     полуо
    0.47
     Най
    0.46
     Paryayvachi
    0.46
    ση
    0.45
    τώ
    0.45
    
    0.45
    Activations Density 0.000%

    No Known Activations