© 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. 5614
    Prev
    Next
    INDEX
    Explanations

    boosting, seeking, strategizing, enforcing, handle

    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
     E
    1.09
     O
    1.06
     J
    1.05
     A
    0.95
     IN
    0.93
     N
    0.89
     Y
    0.89
     D
    0.88
     such
    0.88
     findet
    0.88
    POSITIVE LOGITS
    できる
    1.02
    最適な
    0.93
    スムーズ
    0.92
    できるよう
    0.91
    から
    0.89
    視野
    0.87
    ätzen
    0.84
    .。
    0.84
    ⌞
    0.84
    高品質
    0.83
    Activations Density 0.334%

    No Known Activations