© 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. 45101
    Prev
    Next
    INDEX
    Explanations

    descriptive qualities and states

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

    Generation Alpha

    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
    這是
    0.46
     cannons
    0.46
    즐
    0.46
    جن
    0.43
     itinéraires
    0.43
    灶
    0.43
    由来
    0.43
    տ
    0.42
    ynth
    0.42
    グ
    0.42
    POSITIVE LOGITS
     Publication
    0.57
     ถูก
    0.55
     入っ
    0.54
     품질
    0.52
     ক্ষমতায়
    0.51
     ตรง
    0.50
     पड़े
    0.50
     Dated
    0.50
     Probate
    0.49
     ไป
    0.49
    Activations Density 0.000%

    No Known Activations