© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5164
    Prev
    Next
    INDEX
    Explanations

    software developer roles

    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
    ابق
    0.66
    ային
    0.64
    ़
    0.63
    '{
    0.60
     gunung
    0.59
    iglia
    0.58
    ('=
    0.58
    屇
    0.58
    "_
    0.57
    日記
    0.57
    POSITIVE LOGITS
     ascribe
    0.82
    or
    0.78
     eradicate
    0.78
     extraordinaire
    0.77
    Untuk
    0.75
     Taille
    0.74
     conifers
    0.73
     Utilisez
    0.73
    RE
    0.72
     fieles
    0.72
    Activations Density 0.602%

    No Known Activations