© 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. 206842
    Prev
    Next
    INDEX
    Explanations

    microscopic valleys, を注入, on Friday

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

    biological processes and sequencing

    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
    迵
    0.48
    棫
    0.47
    亣
    0.47
     Zas
    0.46
    崞
    0.45
     தோட்டங்கள்
    0.44
     фотографи
    0.44
     Angaben
    0.43
    荩
    0.43
     Magnificent
    0.43
    POSITIVE LOGITS
    اگر
    0.42
    ऊदी
    0.42
     facilitators
    0.42
    valve
    0.40
     wett
    0.40
    ilateral
    0.39
    WAYS
    0.39
    ulasi
    0.39
    itoria
    0.39
    헹
    0.39
    Activations Density 0.000%

    No Known Activations