© 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. 22-GEMMASCOPE-RES-131K
    7. 129403
    Prev
    Next
    INDEX
    Explanations

    To followed by a verb

    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_22/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
     even
    -1.30
     if
    -1.13
     although
    -1.11
     but
    -1.08
     when
    -1.02
     before
    -1.01
     даже
    -1.00
     also
    -0.98
     tục
    -0.96
     only
    -0.95
    POSITIVE LOGITS
    Therefore
    1.67
     therefore
    1.60
    therefore
    1.48
     Therefore
    1.30
     hivyo
    1.30
     therefor
    1.27
     hiyo
    1.14
     этого
    1.13
    Accordingly
    1.12
    そんな
    1.11
    Activations Density 0.068%

    No Known Activations