© 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. 145049
    Prev
    Next
    INDEX
    Explanations

    quality/usefulness/betterment/action connectors

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

    estimate demographics

    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
     Achieve
    0.50
    </h2>
    0.44
    ASE
    0.44
    iculate
    0.43
     Shape
    0.43
     NASA
    0.42
    btnAdd
    0.42
     Medical
    0.41
     Partner
    0.40
     Word
    0.40
    POSITIVE LOGITS
    아서
    0.55
    ู้
    0.49
     habían
    0.48
     갔
    0.47
    RegistrationBean
    0.47
     tři
    0.46
     של
    0.46
    واع
    0.46
    ુદ્ધ
    0.45
     failings
    0.45
    Activations Density 0.001%

    No Known Activations