© 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. 218321
    Prev
    Next
    INDEX
    Explanations

    expectations and beliefs

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

    fillets, Verify, revolutionized, healing, Extract

    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
    s
    0.55
    the
    0.54
    Д
    0.50
    贲
    0.49
    М
    0.48
    Haupt
    0.48
    w
    0.48
    Marie
    0.46
    Ｓ
    0.46
    ről
    0.45
    POSITIVE LOGITS
     grant
    0.52
     pak
    0.50
     candle
    0.49
     garder
    0.47
     temperament
    0.47
     rappro
    0.46
     adap
    0.46
     rung
    0.46
     reduce
    0.46
     garde
    0.46
    Activations Density 0.001%

    No Known Activations