© 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. 197443
    Prev
    Next
    INDEX
    Explanations

    year immediately preceding

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

    marketplace, yard, locations

    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
    recogn
    0.47
    🌿
    0.46
    さり
    0.46
    sne
    0.45
    deme
    0.44
    াণ
    0.43
    bios
    0.43
    spraak
    0.42
    з
    0.42
    czeniu
    0.42
    POSITIVE LOGITS
     panels
    0.53
     JONES
    0.45
     vortices
    0.45
     панели
    0.45
     guilds
    0.45
    Ks
    0.44
     paneles
    0.44
     उठे
    0.43
     nurseries
    0.43
    RIOT
    0.43
    Activations Density 0.001%

    No Known Activations