© 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. 155710
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings capitalized

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

    technical domain concepts

    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
     workplaces
    0.55
    !।
    0.53
     appending
    0.50
     Νο
    0.50
     LEAR
    0.50
    𝕤
    0.49
     immunoprec
    0.49
    ။
    0.49
     intéressante
    0.48
    ಿಗಳ
    0.48
    POSITIVE LOGITS
    unt
    0.55
    ного
    0.52
    uro
    0.52
    ate
    0.52
    ove
    0.52
    ive
    0.49
    ber
    0.49
    一部
    0.49
    du
    0.48
    bl
    0.48
    Activations Density 0.001%

    No Known Activations