© 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. 15359
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Hungarian
    0.55
    पूर्वी
    0.50
     Negotiations
    0.50
    ListenAndServe
    0.48
     ئێ
    0.48
     Sender
    0.47
     Serbian
    0.47
    <0x15>
    0.46
    Classpath
    0.46
    Negoti
    0.46
    POSITIVE LOGITS
     caches
    1.11
     cache
    0.98
    caches
    0.98
    cache
    0.96
     ~/.
    0.95
     temp
    0.94
    缓存
    0.93
    temp
    0.90
     tempData
    0.88
     Cache
    0.86
    Activations Density 0.176%

    No Known Activations