© 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. 122830
    Prev
    Next
    INDEX
    Explanations

    biblical quotes

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

    global food supply and geopolitical influence

    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
    Რ
    0.55
    érences
    0.49
     மன்னி
    0.46
     சிந்த
    0.45
     並
    0.45
    }/{
    0.45
    CriteriaUtils
    0.44
    JobList
    0.43
     የስ
    0.42
    Ე
    0.42
    POSITIVE LOGITS
     on
    0.50
     SET
    0.46
    eclipse
    0.46
     AG
    0.46
     insurgency
    0.45
     obt
    0.44
     warns
    0.44
     SHOW
    0.43
     by
    0.43
    اتف
    0.43
    Activations Density 0.001%

    No Known Activations