© 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. 24545
    Prev
    Next
    INDEX
    Explanations

    case during

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

    context and situation shifts

    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
    :
    0.48
    又要
    0.47
     requires
    0.43
     Game
    0.43
     required
    0.43
     FedEx
    0.42
     game
    0.42
     will
    0.41
     followers
    0.41
    8
    0.41
    POSITIVE LOGITS
     그것
    0.57
     Preferably
    0.48
     inhomogeneities
    0.48
    それが
    0.47
     관광
    0.46
     इसकी
    0.46
    זה
    0.46
     זה
    0.44
    Это
    0.44
     inhomogeneity
    0.44
    Activations Density 0.000%

    No Known Activations