© 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. 7958
    Prev
    Next
    INDEX
    Explanations

    visual reasoning and appeal

    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
    RIM
    0.70
    apkan
    0.66
     Mattress
    0.65
     यावेळी
    0.65
     latter
    0.64
     brownish
    0.64
    ınt
    0.63
    
    0.63
    ONA
    0.62
     بدن
    0.61
    POSITIVE LOGITS
     arresting
    0.67
     Arrest
    0.64
    aries
    0.60
    ية
    0.60
     cue
    0.59
     cues
    0.58
     👀
    0.57
     arrest
    0.57
    锤
    0.57
     acuity
    0.55
    Activations Density 0.134%

    No Known Activations