© 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. 69275
    Prev
    Next
    INDEX
    Explanations

    hyperbolic discounter

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

    economics and fiction

    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
    莧
    0.46
    みました
    0.44
     Trunk
    0.44
     akin
    0.44
     आईं
    0.43
     analogous
    0.43
     mike
    0.43
     மிக்க
    0.43
    ng
    0.42
     Sparse
    0.42
    POSITIVE LOGITS
    ريقه
    0.52
     furniture
    0.47
    ळे
    0.46
    éros
    0.46
    <0xB8>
    0.45
     secteurs
    0.45
    CENTR
    0.44
    شق
    0.43
    éro
    0.43
    кто
    0.43
    Activations Density 0.000%

    No Known Activations