© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9390
    Prev
    Next
    INDEX
    Explanations

    chart generation and discussion

    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
    '
    2.00
     М
    1.76
    нең
    1.73
     clutch
    1.70
    م
    1.70
     nook
    1.64
    ’
    1.61
    ня
    1.60
     Ver
    1.53
     Assassin
    1.50
    POSITIVE LOGITS
    니다
    2.05
    ación
    2.02
    不清
    1.94
    вання
    1.91
    ıyla
    1.91
    원
    1.91
    αν
    1.90
    舸
    1.90
    િંગ
    1.89
    সারে
    1.89
    Activations Density 0.015%

    No Known Activations