© 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. 105000
    Prev
    Next
    INDEX
    Explanations

    situation, previous, jam

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

    explaining what follows an action or state

    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
     longue
    0.55
     greedy
    0.55
    :
    0.53
    extend
    0.50
     variant
    0.48
     Flow
    0.47
     vip
    0.46
     flow
    0.46
    pre
    0.45
     doubly
    0.45
    POSITIVE LOGITS
    薷
    0.47
    TotalPrice
    0.46
    يرو
    0.45
    ود
    0.45
     население
    0.44
    StudentID
    0.44
    ണാ
    0.43
    िया
    0.43
     наше
    0.43
    महिलाओं
    0.43
    Activations Density 0.000%

    No Known Activations