© 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. 32107
    Prev
    Next
    INDEX
    Explanations

    travel ling including shelf and forms

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

    product design and generation

    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
    은
    0.47
    COPY
    0.45
    olfo
    0.44
    奠
    0.43
     भास्कर
    0.43
    better
    0.43
    terminate
    0.43
    which
    0.43
     Cib
    0.42
    逾
    0.42
    POSITIVE LOGITS
     kab
    0.50
     fiducia
    0.50
     niz
    0.50
     tutti
    0.49
     lalu
    0.49
     suitcases
    0.49
     yang
    0.49
     UPS
    0.49
     vertrou
    0.48
     zom
    0.48
    Activations Density 0.000%

    No Known Activations