© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16
    Prev
    Next
    INDEX
    Explanations

    strong positive descriptors

    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
    Negative Logits
     but
    0.44
     aim
    0.41
    しますが
    0.40
    <0x0D>
    0.39
     use
    0.37
     vorgesehen
    0.37
     include
    0.37
     types
    0.37
     gekennzeichnet
    0.37
    但
    0.36
    POSITIVE LOGITS
     fantastic
    0.91
     Excelente
    0.84
     Очень
    0.81
     terrific
    0.79
     невероят
    0.79
     excellent
    0.78
     Excellent
    0.77
    Excellent
    0.77
     wonderful
    0.76
     incredible
    0.76
    Activations Density 0.439%

    No Known Activations