© 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. 21895
    Prev
    Next
    INDEX
    Explanations

    smooth and make

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

    results-oriented

    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
     papillary
    0.48
     pung
    0.47
    द्धा
    0.46
     puzzled
    0.43
    鰹
    0.43
     raising
    0.42
    ですので
    0.42
     raised
    0.42
     bifurcation
    0.42
     ductility
    0.42
    POSITIVE LOGITS
     ομά
    0.45
    <unused48>
    0.44
     Renaissance
    0.44
    únior
    0.44
     സംസ്
    0.44
    ן
    0.44
    ologiques
    0.44
    一身
    0.44
    ையாள
    0.43
    敚
    0.43
    Activations Density 0.000%

    No Known Activations