© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85807
    Prev
    Next
    INDEX
    Explanations

    Dowling

    np_acts-logits-general · gemini-2.5-flash-lite

    pending and outstanding states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     अत्याधुनिक
    0.50
     magazine
    0.47
     MAGAZINE
    0.47
    Magazine
    0.44
    杂志
    0.43
     लगे
    0.43
     अनाउंस
    0.43
    昀
    0.42
     Magazines
    0.41
     Chairman
    0.40
    POSITIVE LOGITS
    Deletion
    0.43
     delet
    0.43
    folding
    0.43
     systematic
    0.42
     deletion
    0.42
     rescaling
    0.41
     algebraica
    0.40
     lymphatiques
    0.39
     deleting
    0.39
    })]
    0.39
    Activations Density 0.022%

    No Known Activations