© 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
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6777
    Prev
    Next
    INDEX
    Explanations

    Anthropic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Aure
    1.11
     ARI
    1.07
    nsec
    1.05
     Loren
    1.02
    ✥
    1.01
     बालो
    0.99
    ारी
    0.99
     CLA
    0.97
    ℑ
    0.97
    ᾽
    0.96
    POSITIVE LOGITS
    つく
    0.91
     mobilisation
    0.87
    好評
    0.83
     tents
    0.82
    许
    0.82
    friend
    0.80
     Rosenthal
    0.79
     Patel
    0.77
    engagement
    0.76
    カップ
    0.76
    Activations Density 0.013%

    No Known Activations