© 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. 9539
    Prev
    Next
    INDEX
    Explanations

    situations escalating or continuing

    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
     (~
    0.81
     미국
    0.80
     incroy
    0.79
     যুক্তরাজ্যের
    0.77
     increíble
    0.77
     nonprofits
    0.74
     California
    0.74
     microbiome
    0.73
     ~$
    0.73
     außerdem
    0.73
    POSITIVE LOGITS
     whereby
    1.14
     monies
    1.13
    Notwithstanding
    1.06
     envisaged
    0.96
     endeavours
    0.95
    Whilst
    0.95
     utilised
    0.91
     utilising
    0.90
     Whilst
    0.89
     Notwithstanding
    0.89
    Activations Density 0.010%

    No Known Activations