© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 89159
    Prev
    Next
    INDEX
    Explanations

    mathematical and linguistic classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.56
    atars
    0.53
    л
    0.50
    urid
    0.49
    ке
    0.48
    heart
    0.48
     instância
    0.48
    𒈗
    0.48
     olyan
    0.46
    hwar
    0.45
    POSITIVE LOGITS
    σης
    0.58
    できるよう
    0.57
    高さ
    0.54
    ቹ
    0.54
    ડિયા
    0.54
    тата
    0.51
     الدراسي
    0.51
    བྱ
    0.50
    produksi
    0.50
    できるように
    0.49
    Activations Density 0.000%

    No Known Activations