© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16332
    Prev
    Next
    INDEX
    Explanations

    ethical AI assistant

    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_31_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
    、
    0.78
     、,
    0.76
    しますが
    0.74
     、
    0.71
    ﹑
    0.70
    、「
    0.64
    이고
    0.63
    ٬
    0.60
     nhưng
    0.59
    いますが
    0.59
    POSITIVE LOGITS
     various
    0.67
     …
    0.63
     usefulness
    0.61
     substantive
    0.61
     attempts
    0.60
     sources
    0.59
     perceptible
    0.58
     (!)
    0.58
     lor
    0.57
     olika
    0.57
    Activations Density 0.236%

    No Known Activations