© 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. 124438
    Prev
    Next
    INDEX
    Explanations

    making decisions or judgments

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

    against excessive, to manipulate, from information

    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
     сведения
    0.57
     ទ
    0.50
     មាន
    0.49
    AndView
    0.48
    AlignedText
    0.47
     والتي
    0.47
    ExposureTime
    0.47
     одну
    0.47
     乾燥
    0.47
     開始
    0.47
    POSITIVE LOGITS
     cautious
    0.49
    ย
    0.46
    ४
    0.44
    ३
    0.44
    v
    0.44
     sceptical
    0.42
    compet
    0.42
    recorded
    0.42
    डून
    0.41
    βέρ
    0.41
    Activations Density 0.000%

    No Known Activations