© 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. 9446
    Prev
    Next
    INDEX
    Explanations

    stereo

    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
    rater
    0.52
    όν
    0.50
    éch
    0.48
    rete
    0.48
    壮
    0.48
    下方
    0.47
    brook
    0.46
    âts
    0.46
    év
    0.46
    these
    0.46
    POSITIVE LOGITS
     уви
    0.64
     機械
    0.57
     Tow
    0.57
     vimos
    0.56
     Pow
    0.55
     pj
    0.55
     stateMutability
    0.54
     noun
    0.54
     towels
    0.54
     `=`
    0.54
    Activations Density 0.000%

    No Known Activations