© 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. 84821
    Prev
    Next
    INDEX
    Explanations

    Fear, second, joke, transformations, choice, law

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

    laboratory information system

    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
     chunks
    0.39
     tours
    0.38
     FUNCTIONS
    0.38
     tore
    0.37
    urée
    0.37
    zhu
    0.37
    廂
    0.37
    ாண்ட
    0.37
    лардан
    0.36
     অনুষ্ঠানে
    0.36
    POSITIVE LOGITS
    ともに
    0.46
    ძლი
    0.45
    without
    0.43
    success
    0.42
    ágot
    0.42
     Ky
    0.42
    rainbow
    0.42
     Cyber
    0.42
     addirittura
    0.41
    🙏
    0.41
    Activations Density 0.000%

    No Known Activations