© 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. 23142
    Prev
    Next
    INDEX
    Explanations

    graphs and charts showing changes

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

    graphs, maps, relationship

    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
     worksheets
    0.46
    憶
    0.44
    describe
    0.43
    tableName
    0.43
     विवरण
    0.42
    onyms
    0.40
     Burundi
    0.40
    たとえば
    0.40
    nist
    0.40
    TableModel
    0.40
    POSITIVE LOGITS
    สี
    0.50
     그래프
    0.49
     graphically
    0.47
    ืด
    0.46
     လ
    0.46
    曲线
    0.45
    叠
    0.45
     superimposed
    0.45
     색
    0.44
     رنگ
    0.43
    Activations Density 0.001%

    No Known Activations