© 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. 158543
    Prev
    Next
    INDEX
    Explanations

    Marbella service grandparents segmentation course

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

    command execution

    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
    恝
    0.46
    ホル
    0.46
    这
    0.44
    オリ
    0.43
     שם
    0.42
     حامل
    0.42
     거기에
    0.42
     आढळ
    0.42
    新た
    0.41
     ফেলা
    0.41
    POSITIVE LOGITS
    c
    0.53
    ᴗ
    0.47
     dd
    0.47
     proprie
    0.46
    component
    0.46
     effect
    0.46
    7
    0.46
     hh
    0.46
     eq
    0.45
     clás
    0.45
    Activations Density 0.001%

    No Known Activations