© 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. 200297
    Prev
    Next
    INDEX
    Explanations

    Valuable accidents, days, Jesus, Maps, equipment

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

    probabilities of outcomes

    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
    ⵎ
    0.54
     gib
    0.47
     np
    0.47
    ום
    0.46
     undetermined
    0.46
    仑
    0.45
    нном
    0.45
     Gib
    0.44
     NP
    0.44
    ཥ
    0.43
    POSITIVE LOGITS
    DataTable
    0.48
     విధంగా
    0.47
    ex
    0.46
     अरुण
    0.45
     య
    0.45
     小物
    0.45
     lavoro
    0.45
    Accounts
    0.44
    oc
    0.44
    Resources
    0.44
    Activations Density 0.001%

    No Known Activations