© 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. 211046
    Prev
    Next
    INDEX
    Explanations

    growth stage

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

    SELECT, Beryllium, IMAGE ID, anesthesiologists, Student

    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
     emblematic
    0.50
     cardiaque
    0.47
     flaves
    0.46
    争
    0.45
     iso
    0.45
     записи
    0.45
     ocul
    0.44
    onClick
    0.44
    エンジン
    0.44
     انجن
    0.43
    POSITIVE LOGITS
    ung
    0.52
    unst
    0.46
    يند
    0.46
    ιν
    0.45
    Union
    0.44
    統
    0.44
    otten
    0.44
    ਿਤ
    0.43
    imin
    0.43
     súa
    0.42
    Activations Density 0.001%

    No Known Activations