© 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. 18810
    Prev
    Next
    INDEX
    Explanations

    thank you

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

    expressing thanks

    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
     lanç
    0.54
     comienzo
    0.49
     lanz
    0.49
     begr
    0.48
     slalom
    0.47
     Lyft
    0.47
     inici
    0.46
     o
    0.46
     admire
    0.46
     zainteres
    0.46
    POSITIVE LOGITS
    ONO
    0.46
    toUpperCase
    0.45
    diameter
    0.42
    Formatted
    0.42
    Compressed
    0.41
    Entity
    0.40
    gax
    0.40
     morphologies
    0.40
     epitope
    0.40
     Boutique
    0.40
    Activations Density 0.029%

    No Known Activations