© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105223
    Prev
    Next
    INDEX
    Explanations

    welcome you back

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

    followed, followed by legal cases

    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
     bilgis
    0.60
     japones
    0.52
    مة
    0.51
     marché
    0.51
    菜
    0.50
    řen
    0.50
    げ
    0.49
    市場
    0.49
     mercado
    0.49
    聯
    0.48
    POSITIVE LOGITS
     Opportun
    0.53
    );
    0.48
     (
    0.48
     Motor
    0.48
     Lynx
    0.46
    ),
    0.45
     External
    0.45
     Orthodox
    0.45
     Dra
    0.45
     Inspect
    0.45
    Activations Density 0.000%

    No Known Activations