© 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. 8187
    Prev
    Next
    INDEX
    Explanations

    numerical computing and sequence manipulation

    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
     spos
    0.58
    ारी
    0.55
     somewhere
    0.55
    лно
    0.54
     desenvolver
    0.53
     милли
    0.52
    herr
    0.52
    ਦ
    0.52
    𝓌
    0.52
     volume
    0.52
    POSITIVE LOGITS
     Num
    0.61
    Numerical
    0.59
    Numeral
    0.56
    क्ति
    0.55
    ismatic
    0.54
    🍟
    0.54
    稳定性
    0.54
     Numerical
    0.53
     Tallinn
    0.52
    лива
    0.52
    Activations Density 0.077%

    No Known Activations