© 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-16K
    7. 10755
    Prev
    Next
    INDEX
    Explanations

    most / least comparative

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    it
    1.41
    of
    1.38
    ì
    1.35
    ità
    1.26
    ò
    1.23
    bbene
    1.21
    iano
    1.20
    ită
    1.19
    ia
    1.17
    id
    1.14
    POSITIVE LOGITS
     hardest
    1.14
     lowest
    1.05
     desirable
    1.04
    𝓵
    1.04
     very
    1.02
    })}$
    1.02
     toughest
    1.01
     coldest
    1.00
    初代
    1.00
     Coolidge
    0.99
    Activations Density 0.765%

    No Known Activations