© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34847
    Prev
    Next
    INDEX
    Explanations

    bristling with

    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
     robes
    1.09
    س
    1.08
    िक
    1.05
     incompetence
    1.03
     cereals
    0.99
    ной
    0.99
     imperialism
    0.98
    ского
    0.97
     reyes
    0.97
     выз
    0.95
    POSITIVE LOGITS
    THING
    1.36
    Nä
    1.32
    ኵ
    1.28
    䯩
    1.12
    Marca
    1.09
    taine
    1.09
    associazione
    1.09
    汐
    1.09
    㻁
    1.09
    accompagn
    1.08
    Activations Density 0.000%

    No Known Activations