© 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. 48200
    Prev
    Next
    INDEX
    Explanations

    gift wrapping

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

    specifications

    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
    輝
    0.48
    ほと
    0.44
     sirven
    0.41
     muchos
    0.41
     calcular
    0.39
    ネート
    0.39
     férfi
    0.38
    Adv
    0.38
     muchas
    0.38
    談
    0.38
    POSITIVE LOGITS
    amen
    0.54
     პირ
    0.52
    datap
    0.52
    ottom
    0.51
    cript
    0.50
    ecommerce
    0.50
    ק
    0.50
    reiben
    0.49
     anonymity
    0.49
    चारा
    0.49
    Activations Density 0.000%

    No Known Activations