© 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. 26105
    Prev
    Next
    INDEX
    Explanations

    financial, international, bribes

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

    ratios and comparisons

    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
     (
    0.61
    ר
    0.57
    ה
    0.52
    ul
    0.51
    w
    0.50
    za
    0.48
    well
    0.48
     =
    0.47
    atau
    0.47
    alled
    0.47
    POSITIVE LOGITS
     financières
    0.55
     financieras
    0.53
     financeiros
    0.52
     hausse
    0.51
     ঘুষ
    0.51
     financieros
    0.48
     पीएफआई
    0.47
     ponieważ
    0.47
    真實
    0.47
     بسبب
    0.47
    Activations Density 0.000%

    No Known Activations