© 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. 137514
    Prev
    Next
    INDEX
    Explanations

    cooking, war, compliance

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

    non-english characters

    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
    animation
    0.54
    d
    0.53
    end
    0.52
     corp
    0.52
    dine
    0.52
    trans
    0.50
    )
    0.50
     is
    0.50
     was
    0.50
    abr
    0.50
    POSITIVE LOGITS
    ูน
    0.57
    ilarly
    0.50
    𝑵
    0.50
     پژ
    0.50
     പിന്തു
    0.49
    ܀
    0.49
    𝑈
    0.47
     المعادله
    0.47
    ぬいぐるみ
    0.47
     جوړونک
    0.46
    Activations Density 0.000%

    No Known Activations