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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3509
    Prev
    Next
    INDEX
    Explanations

    programming keywords and access modifiers

    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_16k_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
    లుగా
    1.09
     étudier
    1.05
    vā
    0.99
    they
    0.98
    くださ
    0.98
    ся
    0.97
    𝓉
    0.96
     partant
    0.96
    ля
    0.95
    𝓭
    0.95
    POSITIVE LOGITS
     biệt
    1.09
    ities
    0.91
    ec
    0.89
     năng
    0.89
    ilyn
    0.89
    ACTIONS
    0.88
    ంట
    0.84
    述
    0.83
    </h6>
    0.82
    </h4>
    0.82
    Activations Density 0.101%

    No Known Activations