© 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. 128228
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
     міся
    -1.19
    tioners
    -1.18
     its
    -1.18
    迅速
    -1.16
    }$
    -1.16
     діяльності
    -1.15
    但
    -1.14
     And
    -1.13
     That
    -1.13
     повіт
    -1.13
    POSITIVE LOGITS
    Produktion
    1.24
    Mitte
    1.19
     deviennent
    1.19
    Aufbau
    1.18
    Karten
    1.16
    察觉
    1.14
    坭
    1.14
     Bluffs
    1.13
    Huhu
    1.13
    Dicas
    1.13
    Activations Density 0.003%

    No Known Activations