© 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. 246382
    Prev
    Next
    INDEX
    Explanations

    select your, make, work

    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
    s
    0.56
     nisso
    0.52
     rugs
    0.51
     ito
    0.48
     creato
    0.47
     dedicada
    0.47
     criada
    0.47
     Rivers
    0.46
     milites
    0.46
     nariz
    0.45
    POSITIVE LOGITS
    觚
    0.49
    ほとんど
    0.45
     अटेम्प्ट
    0.45
    申し込み
    0.43
    Ко
    0.43
    ム
    0.43
    硖
    0.43
    Пра
    0.42
    鰯
    0.42
    ặn
    0.41
    Activations Density 0.001%

    No Known Activations