© 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. 34323
    Prev
    Next
    INDEX
    Explanations

    decades 70s 80s 90s

    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
     this
    -1.58
    !!!!
    -1.51
    d
    -1.48
    !!!!!
    -1.48
    2
    -1.40
    H
    -1.38
    g
    -1.36
    !!!
    -1.34
     with
    -1.33
    In
    -1.31
    POSITIVE LOGITS
     pistolet
    1.48
     siè
    1.45
    melden
    1.41
     uſed
    1.40
     keramik
    1.38
     tempel
    1.36
    käse
    1.35
    
    1.34
     minimalis
    1.34
    thee
    1.33
    Activations Density 0.021%

    No Known Activations