© 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. 91703
    Prev
    Next
    INDEX
    Explanations

    logistics, rental, credit, site

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

    potential gains and assessment

    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
     सेंट्रल
    0.48
    ständen
    0.46
    ühr
    0.45
    ъз
    0.45
    ilden
    0.43
     ANGE
    0.42
    薛
    0.41
     تي
    0.41
    hely
    0.41
    vět
    0.41
    POSITIVE LOGITS
     adhesions
    0.53
    ラの
    0.51
     freck
    0.50
     terbentuk
    0.49
    owano
    0.49
     kesel
    0.48
     Laff
    0.47
    hands
    0.46
     dialogues
    0.45
     නමුත්
    0.45
    Activations Density 0.001%

    No Known Activations