© 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. 227656
    Prev
    Next
    INDEX
    Explanations

    place names and entities

    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
    UT
    0.51
     हाता
    0.47
    GC
    0.45
    ک
    0.43
    akan
    0.43
    meshes
    0.43
     لیک
    0.42
    meli
    0.42
    ARAJ
    0.42
    ylim
    0.42
    POSITIVE LOGITS
    内容
    0.49
    之所以
    0.45
     laboratoire
    0.45
     condemn
    0.45
     Tiến
    0.45
    排名
    0.44
    Hv
    0.44
    铤
    0.44
    到底是
    0.44
     Avner
    0.44
    Activations Density 0.000%

    No Known Activations