© 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. 12-GEMMASCOPE-2-RES-262K
    7. 40335
    Prev
    Next
    INDEX
    Explanations

    voicing, hoisting, articul, ceteris paribus

    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_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     neglig
    1.34
     olefins
    1.33
     heirs
    1.32
    O
    1.28
    нде
    1.27
    нку
    1.27
    ף
    1.27
     internas
    1.25
    트는
    1.24
     Tots
    1.23
    POSITIVE LOGITS
    dte
    1.45
    ý
    1.45
    َس
    1.41
    াতা
    1.38
    n
    1.32
    ste
    1.31
    സ
    1.30
    ames
    1.28
    anger
    1.28
    es
    1.25
    Activations Density 0.001%

    No Known Activations