© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85093
    Prev
    Next
    INDEX
    Explanations

    should have + past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oys
    -1.57
     semmi
    -1.56
    Tango
    -1.56
    
    -1.41
     celles
    -1.41
    品の
    -1.41
    Gilla
    -1.40
     може
    -1.38
    abaikan
    -1.37
    obacz
    -1.34
    POSITIVE LOGITS
    2
    1.84
    t
    1.66
    on
    1.61
    7
    1.61
    In
    1.60
    it
    1.49
     they
    1.48
    5
    1.41
    at
    1.34
    克斯
    1.32
    Activations Density 0.010%

    No Known Activations