© 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. 64759
    Prev
    Next
    INDEX
    Explanations

    causal pathways

    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
     ᾿
    -1.42
     \'
    -1.38
     Poehler
    -1.31
     alcune
    -1.28
    に関しては
    -1.27
     baha
    -1.25
     салон
    -1.20
    芘
    -1.20
     capitán
    -1.17
     peugeot
    -1.16
    POSITIVE LOGITS
     or
    1.63
    หรือ
    1.50
    niña
    1.45
     vaš
    1.45
     use
    1.45
     elevada
    1.43
     všetkých
    1.42
     budete
    1.39
    достатки
    1.38
    ländische
    1.35
    Activations Density 0.019%

    No Known Activations