© 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. 822
    Prev
    Next
    INDEX
    Explanations

    rx

    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
    ራል
    0.64
    }$;
    0.62
    !;
    0.62
     أحمد
    0.60
     おしゃれ
    0.59
     princípio
    0.59
     چاہیے
    0.57
     comércio
    0.57
    ــــ
    0.56
     メル
    0.56
    POSITIVE LOGITS
    .
    1.46
    ._
    1.35
    ().
    1.27
    。
    1.12
    _.
    1.09
    .$
    1.06
    .__
    1.06
    ‌.
    1.05
    .{
    0.97
    .%
    0.94
    Activations Density 0.479%

    No Known Activations