© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27539
    Prev
    Next
    INDEX
    Explanations

    Microvessel or Satan

    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
    猹
    -1.53
    嫫
    -1.36
     ané
    -1.36
    杙
    -1.34
    ```
    -1.28
     irland
    -1.28
     selam
    -1.27
     úl
    -1.27
     lavable
    -1.27
     शुर
    -1.24
    POSITIVE LOGITS
    {
    1.42
    ]
    1.37
    (
    1.37
     osserv
    1.30
     the
    1.20
     całkow
    1.16
    似た
    1.16
    みると
    1.14
     mogą
    1.14
    ha
    1.13
    Activations Density 0.000%

    No Known Activations