© 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. 228667
    Prev
    Next
    INDEX
    Explanations

    subscribe to podcast

    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
    iming
    0.51
    ❈
    0.50
    lige
    0.45
    phthalm
    0.45
    ማሪ
    0.45
    㤈
    0.45
    oddsidemargin
    0.44
    atrice
    0.44
    Namara
    0.44
    opsy
    0.44
    POSITIVE LOGITS
     geldi
    0.49
     kau
    0.47
     spectrum
    0.46
     cadenas
    0.45
     untouched
    0.44
     lubricating
    0.44
     deu
    0.44
    牒
    0.43
    んですが
    0.43
     taxing
    0.43
    Activations Density 0.001%

    No Known Activations