© 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. 130208
    Prev
    Next
    INDEX
    Explanations

    inside out

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

    explaining requirements or features

    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
    outputs
    0.52
     Outputs
    0.50
    ксе
    0.49
    કારો
    0.48
    κης
    0.47
    hiq
    0.46
    셍
    0.46
    zess
    0.45
    自身の
    0.44
    ضح
    0.43
    POSITIVE LOGITS
    oz
    0.49
    WP
    0.47
    ৯
    0.47
     TFS
    0.46
    oon
    0.45
     figurines
    0.44
     enfin
    0.44
    WF
    0.44
     Devil
    0.43
    WI
    0.43
    Activations Density 0.000%

    No Known Activations