© 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. 102308
    Prev
    Next
    INDEX
    Explanations

    sophisticated furniture design

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

    specific phrases and academic terms

    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
    n
    0.53
    lefthar
    0.50
    as
    0.48
     Praha
    0.47
    flamingo
    0.47
    es
    0.46
    chefs
    0.46
    ského
    0.45
    quera
    0.45
    hz
    0.45
    POSITIVE LOGITS
    א
    0.54
     conducive
    0.46
    чит
    0.45
     ય
    0.45
     irrigated
    0.45
     सिंचाई
    0.44
     разрешения
    0.44
     photosynthesis
    0.44
    ینه
    0.44
     अवैध
    0.43
    Activations Density 0.000%

    No Known Activations