© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 11866
    Prev
    Next
    INDEX
    Explanations

    Select, export, and file options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    udos
    0.91
    стоя
    0.87
    RECEIVED
    0.84
    ⌒
    0.80
    ovid
    0.79
     қили
    0.78
    together
    0.78
    懂
    0.78
     трево
    0.78
    מע
    0.78
    POSITIVE LOGITS
     Bachelors
    0.96
     slew
    0.95
     orthogonality
    0.93
     urethra
    0.93
     Cemetery
    0.93
    ኗ
    0.92
     Въ
    0.92
     Nationalist
    0.91
     Dateien
    0.91
    ി
    0.90
    Activations Density 0.002%

    No Known Activations