© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7551
    Prev
    Next
    INDEX
    Explanations

    cannot provide

    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
     akár
    0.66
     էր
    0.64
     kanske
    0.62
     Particular
    0.61
    _{+}+
    0.61
     knowledgeable
    0.60
     particulière
    0.58
     magari
    0.58
    त्सा
    0.56
    葺
    0.56
    POSITIVE LOGITS
     cannot
    1.00
    cannot
    0.97
     Cannot
    0.82
    Cannot
    0.78
     illegally
    0.77
     ilegal
    0.73
     unauthorized
    0.71
    illegal
    0.70
    自分で
    0.69
     illegal
    0.68
    Activations Density 0.452%

    No Known Activations