© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6840
    Prev
    Next
    INDEX
    Explanations

    recipe serving sizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hesion
    0.69
     vertebrate
    0.68
     precedes
    0.64
     коро
    0.63
     sits
    0.63
    }=$
    0.62
     Brownian
    0.61
    )<-
    0.60
    ব্রিটিশ
    0.60
    man
    0.60
    POSITIVE LOGITS
    いつも
    0.88
     čin
    0.79
     több
    0.76
    状況
    0.75
    зре
    0.74
     perasaan
    0.74
    प्रति
    0.74
    多くの
    0.74
     مُعرِّف
    0.74
    र्मा
    0.73
    Activations Density 0.004%

    No Known Activations