© 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. 224614
    Prev
    Next
    INDEX
    Explanations

    popular massage clinic

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

    trading offers

    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
    সাব
    0.52
    nbr
    0.50
    വരെ
    0.49
    wsdl
    0.49
    urais
    0.48
    factorplot
    0.48
    myName
    0.47
     ಒ
    0.47
    fak
    0.46
     എല്ലാം
    0.46
    POSITIVE LOGITS
     terse
    0.48
    .
    0.46
     Grafik
    0.45
     twitter
    0.45
     grafik
    0.44
    居家
    0.44
    碉
    0.44
     discrete
    0.43
     térmica
    0.43
     жөнүндө
    0.42
    Activations Density 0.000%

    No Known Activations