© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10839
    Prev
    Next
    INDEX
    Explanations

    Service in code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ﺕ
    1.90
    有所
    1.81
     sola
    1.76
    )};
    1.70
    s
    1.68
    滪
    1.66
     teclas
    1.62
    ﻙ
    1.60
     soweit
    1.59
    意味着
    1.57
    POSITIVE LOGITS
    ס
    1.77
    ia
    1.59
    gning
    1.55
    1
    1.55
    ю
    1.52
    gies
    1.51
    2
    1.50
    9
    1.48
    grammar
    1.46
    тів
    1.45
    Activations Density 0.018%

    No Known Activations