© 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. 41040
    Prev
    Next
    INDEX
    Explanations

    being king

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

    binary logic

    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
    on
    0.54
    ack
    0.50
    cdf
    0.48
    也
    0.46
    az
    0.46
    obs
    0.46
    空
    0.46
    nf
    0.46
    apt
    0.45
    ard
    0.45
    POSITIVE LOGITS
     стороны
    0.53
     carcinomas
    0.53
     جناب
    0.53
     потре
    0.50
     صحی
    0.50
     labyr
    0.49
     всех
    0.48
     капита
    0.48
     ਅ
    0.48
     unrival
    0.48
    Activations Density 0.000%

    No Known Activations