© 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. 89763
    Prev
    Next
    INDEX
    Explanations

    them they

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

    generating intricate descriptions

    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
    出来る
    0.55
     сожалению
    0.50
    OLY
    0.47
     пришлось
    0.47
    リッジ
    0.46
     позволит
    0.45
    ようやく
    0.45
    <iframe>
    0.44
    OLD
    0.44
     এট
    0.44
    POSITIVE LOGITS
     nano
    0.52
     Biotechn
    0.50
     Nano
    0.49
     chill
    0.48
     di
    0.46
     kindergarten
    0.45
     watch
    0.45
     sweep
    0.44
     bho
    0.44
    kere
    0.44
    Activations Density 0.002%

    No Known Activations