© 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. 52695
    Prev
    Next
    INDEX
    Explanations

    issue

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

    specific technical terms

    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
     platforms
    0.49
    CNN
    0.49
     sanctions
    0.49
    ZA
    0.47
     markets
    0.46
    P
    0.46
     prices
    0.46
     parcels
    0.46
    Refer
    0.43
     clinics
    0.43
    POSITIVE LOGITS
     precisamente
    0.57
     वृद्धा
    0.54
     場所
    0.53
     コンパクト
    0.50
    itamento
    0.50
     арифмети
    0.49
    íduos
    0.49
     मिरची
    0.48
    ઈ
    0.48
     justamente
    0.47
    Activations Density 0.000%

    No Known Activations