© 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. 163627
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    lengths of quantities

    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
     data
    0.32
     nonzero
    0.31
     $
    0.30
     SaaS
    0.30
     x
    0.29
     variables
    0.29
     regex
    0.29
     analysis
    0.28
     values
    0.28
     volatile
    0.28
    POSITIVE LOGITS
    Église
    0.29
    Musik
    0.28
    Mountains
    0.26
    Giov
    0.26
     pięk
    0.26
    Stadt
    0.25
     церков
    0.25
    Mediterranean
    0.25
    Accueil
    0.25
    酺
    0.25
    Activations Density 0.000%

    No Known Activations