© 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. 40255
    Prev
    Next
    INDEX
    Explanations

    capped peaks, power of, class of

    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
    ad
    1.37
    um
    1.23
    ec
    1.16
    ów
    1.13
    SL
    1.08
    T
    1.08
    ul
    1.07
    un
    1.06
    ný
    1.05
    é
    1.04
    POSITIVE LOGITS
    पचारिक
    1.19
     ditth
    1.05
     logement
    1.05
    ᆸ
    1.03
     prawn
    1.02
     termites
    1.02
     APAC
    1.01
     vutt
    0.98
     insiders
    0.98
    நாயகம்
    0.98
    Activations Density 0.000%

    No Known Activations