© 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. 17075
    Prev
    Next
    INDEX
    Explanations

    medical or scientific terms

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

    medical and scientific terms

    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
    umni
    0.44
    iden
    0.41
     covenant
    0.41
    简称
    0.41
     Surplus
    0.40
     parties
    0.40
    avier
    0.40
    鈥
    0.40
    aws
    0.39
    ave
    0.39
    POSITIVE LOGITS
     medicina
    0.59
     vírus
    0.57
     paralysie
    0.54
     Biochim
    0.54
     Arzneim
    0.52
     enzimas
    0.50
     diosa
    0.50
     médicaments
    0.50
     médecine
    0.50
     Drei
    0.50
    Activations Density 0.000%

    No Known Activations