© 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. 28561
    Prev
    Next
    INDEX
    Explanations

    invests in or buys

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

    financial protection

    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
    ass
    0.46
     الق
    0.46
    増
    0.43
    cours
    0.42
    end
    0.42
     هذه
    0.40
     mdl
    0.39
     magnific
    0.38
    順
    0.38
    时刻
    0.38
    POSITIVE LOGITS
     pabbaj
    0.55
    .??.??"]
    0.55
     SupCt
    0.52
    אר
    0.51
     inhomogeneities
    0.49
     denominators
    0.48
     justices
    0.47
     involunt
    0.47
     വെള്ള
    0.47
     ෆ
    0.47
    Activations Density 0.000%

    No Known Activations