© 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. 26444
    Prev
    Next
    INDEX
    Explanations

    phrase starters

    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
     faciliter
    -1.40
    hundreds
    -1.35
     siè
    -1.33
     BadRequest
    -1.31
     perpé
    -1.27
     தமி
    -1.27
    often
    -1.25
    irée
    -1.23
     olika
    -1.23
    .*;
    -1.23
    POSITIVE LOGITS
     your
    2.55
     this
    2.30
     you
    2.14
     máte
    1.40
     now
    1.34
     will
    1.32
     zrobić
    1.32
    ḻ
    1.31
     YOU
    1.29
     خواهید
    1.28
    Activations Density 0.010%

    No Known Activations