© 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. 124950
    Prev
    Next
    INDEX
    Explanations

    information and context

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

    experiencing resurgence or common recovery

    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
    ’
    0.57
    '
    0.54
     requirement
    0.53
     menentukan
    0.53
    0
    0.52
    9
    0.50
     suggestion
    0.46
     heel
    0.46
     I
    0.45
     requiring
    0.45
    POSITIVE LOGITS
     Poincaré
    0.50
    stände
    0.47
    िटी
    0.46
    thebetter
    0.46
     المرسلين
    0.46
    تمبر
    0.45
     Disputes
    0.45
    𒋾
    0.45
    叕
    0.45
    琙
    0.45
    Activations Density 0.001%

    No Known Activations