© 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. 21062
    Prev
    Next
    INDEX
    Explanations

    instructions for use

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

    fantasy, simulation, reality

    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
     Ces
    0.40
    NETT
    0.39
    ache
    0.39
     табы
    0.38
    杼
    0.38
    Ces
    0.37
     किनार
    0.37
    锜
    0.37
    Elems
    0.36
    शिता
    0.36
    POSITIVE LOGITS
    0.38
     IconButton
    0.37
    uhe
    0.37
     Nxg
    0.37
     Lauderdale
    0.37
    夏季
    0.36
    rech
    0.36
     -(
    0.36
     lofty
    0.35
     地址
    0.35
    Activations Density 0.192%

    No Known Activations