© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    signality or dressing

    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
     '
    1.39
    '.
    1.23
     scorso
    1.21
    _.
    1.16
    過了
    1.16
    檛
    1.15
    がら
    1.14
    ''
    1.13
    を聞
    1.13
     répart
    1.11
    POSITIVE LOGITS
    s
    1.84
    ের
    1.83
    า
    1.81
    ों
    1.70
    ла
    1.53
    y
    1.52
    ar
    1.49
    ار
    1.48
    ти
    1.43
    י
    1.41
    Activations Density 0.033%

    No Known Activations