© 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. 250668
    Prev
    Next
    INDEX
    Explanations

    product specific terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ક્
    0.42
    ted
    0.42
    ţ
    0.42
     लाखों
    0.40
    бліоте
    0.40
    ﾌ
    0.40
    бо
    0.40
    掍
    0.40
    𝘁
    0.39
    ьо
    0.39
    POSITIVE LOGITS
     bimod
    0.55
     razlik
    0.51
     osobow
    0.50
     sphinct
    0.50
     doença
    0.49
     gingham
    0.49
     maladie
    0.48
     demeure
    0.48
     bhav
    0.47
     myocardium
    0.47
    Activations Density 0.000%

    No Known Activations