© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213412
    Prev
    Next
    INDEX
    Explanations

    phishing, vehicle, consumption, shop, blogging, age, twin, reported

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

    installedratecertificatesstatusalive

    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
    Negative Logits
     dispuestos
    0.47
     ($
    0.44
     Scores
    0.44
     (${
    0.41
    成績
    0.41
    iaus
    0.41
    Index
    0.41
    ataires
    0.41
    },{"
    0.41
    他に
    0.40
    POSITIVE LOGITS
     ጥላ
    0.48
     அப்பா
    0.45
     vex
    0.43
     piezo
    0.43
     पादु
    0.42
    लाइट
    0.41
    Ϻ
    0.41
    Rite
    0.41
    Salman
    0.40
    🚘
    0.40
    Activations Density 0.001%

    No Known Activations