© 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. 72329
    Prev
    Next
    INDEX
    Explanations

    identifying foundations and relationships

    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
     району
    -0.96
     several
    -0.94
     during
    -0.94
     роза
    -0.93
     Commen
    -0.93
     they
    -0.90
     воспользова
    -0.90
    Tomasz
    -0.90
     most
    -0.89
     twenty
    -0.88
    POSITIVE LOGITS
     latine
    1.19
    ILAR
    1.03
    另一
    1.02
    usually
    1.02
    ఎ
    1.00
    formazioni
    0.98
    $~
    0.98
    ᕮ
    0.96
     animale
    0.96
     lampa
    0.94
    Activations Density 0.062%

    No Known Activations