© 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. 210873
    Prev
    Next
    INDEX
    Explanations

    evolutionary lineage, legislation, supervision, next course, car sale, direct marketing

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

    building and detection

    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
    哏
    0.47
    uradaki
    0.46
     sayesinde
    0.44
    ᵖ
    0.44
     ঘাট
    0.44
     понадоби
    0.44
     ఆయన
    0.43
     এগুলো
    0.43
     адрес
    0.43
    odigd
    0.43
    POSITIVE LOGITS
    Mamm
    0.44
    Oreal
    0.42
    Election
    0.40
    OMO
    0.40
     सरिया
    0.39
     Leach
    0.39
    别墅
    0.39
    S
    0.39
     twofold
    0.38
    Molecular
    0.38
    Activations Density 0.001%

    No Known Activations