© 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. 242462
    Prev
    Next
    INDEX
    Explanations

    art gallery museum Exposition

    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
     gele
    0.51
     kov
    0.49
     CSR
    0.46
     sami
    0.46
     ";//
    0.46
    美味
    0.46
     coinbase
    0.45
    "<<
    0.44
    ര്‍
    0.44
     vz
    0.44
    POSITIVE LOGITS
    Museum
    0.49
    Gallery
    0.47
     Exposition
    0.47
    Checker
    0.46
    Chrome
    0.46
    Exporter
    0.45
     Gallery
    0.44
     hará
    0.43
     Collage
    0.42
     انہوں
    0.42
    Activations Density 0.000%

    No Known Activations