© 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. 7691
    Prev
    Next
    INDEX
    Explanations

    rust code elements

    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
     cowboy
    0.61
     achieving
    0.60
    穎
    0.57
     pub
    0.57
     يوليو
    0.55
     seemingly
    0.53
     mencapai
    0.53
     trinity
    0.53
     structs
    0.53
     opa
    0.52
    POSITIVE LOGITS
    Option
    0.92
     &
    0.89
     Option
    0.87
    &
    0.82
    (&
    0.79
    mut
    0.75
    option
    0.74
    &$
    0.71
     (&
    0.70
     option
    0.68
    Activations Density 0.080%

    No Known Activations