© 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. 47899
    Prev
    Next
    INDEX
    Explanations

    organic disinfectants

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

    balsamic glaze or evaluation metrics

    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
     Zahl
    0.49
     التى
    0.46
     ziehen
    0.46
     Wasser
    0.46
    ucch
    0.45
     Rup
    0.45
     ר
    0.45
     خلف
    0.45
     marshmallows
    0.45
     Titel
    0.45
    POSITIVE LOGITS
     síndrome
    0.49
     viaj
    0.48
    抗
    0.48
     negó
    0.46
    涪
    0.46
    郊
    0.45
    ἤ
    0.45
     preocupa
    0.44
    DAV
    0.43
    姫
    0.43
    Activations Density 0.000%

    No Known Activations