© 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. 174891
    Prev
    Next
    INDEX
    Explanations

    tax rate

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

    appetizers and starters

    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
    ו
    0.47
     đem
    0.46
    Clusters
    0.44
    商
    0.43
    Peak
    0.43
    Acet
    0.42
    Ack
    0.42
    Notably
    0.42
    Mg
    0.42
    Isopropyl
    0.42
    POSITIVE LOGITS
    bbc
    0.47
    robespierre
    0.46
     इंट्रो
    0.46
    গরে
    0.46
    꺅
    0.45
    elitian
    0.44
    aquin
    0.43
     pembang
    0.43
    avage
    0.43
     खासदार
    0.42
    Activations Density 0.001%

    No Known Activations