© 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. 175537
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    account privacy

    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
    危机
    0.46
     منفی
    0.46
    フォルト
    0.46
    றிய
    0.45
    clicking
    0.43
    뢰
    0.42
     விகி
    0.42
    σης
    0.41
    .«
    0.41
    Bitte
    0.41
    POSITIVE LOGITS
     he
    0.48
     occupies
    0.48
     accounts
    0.46
     account
    0.45
     interchange
    0.45
     audio
    0.45
     उसने
    0.44
     asam
    0.44
     他
    0.44
     multicolor
    0.44
    Activations Density 0.006%

    No Known Activations