© 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. 250879
    Prev
    Next
    INDEX
    Explanations

    medical reconstitution and ultrasound

    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
    깅
    0.52
    ్వ
    0.51
    ત્મક
    0.50
    ಿಣ
    0.48
     llrp
    0.47
    ાલ
    0.46
    бет
    0.46
    ниципа
    0.46
    尟
    0.46
    بوون
    0.46
    POSITIVE LOGITS
    0.49
    ’
    0.46
     Protocol
    0.45
     Division
    0.44
     Intervals
    0.44
     Disease
    0.43
     Religion
    0.43
     Illness
    0.43
     Distributor
    0.42
     Hz
    0.42
    Activations Density 0.000%

    No Known Activations