© 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. 10-GEMMASCOPE-RES-131K
    7. 85989
    Prev
    Next
    INDEX
    Explanations

    function options or parameters

    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_10/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
     eventual
    -1.35
     zeker
    -1.22
     facilidad
    -1.20
    eventually
    -1.15
     locura
    -1.13
    Pcd
    -1.11
     in
    -1.10
     say
    -1.09
    }}-\
    -1.09
     gener
    -1.07
    POSITIVE LOGITS
     criteria
    1.30
     espanhol
    1.23
    設計
    1.22
     նաև
    1.21
    vants
    1.18
     conditions
    1.16
    utivos
    1.16
     табли
    1.14
     selben
    1.14
    其
    1.13
    Activations Density 0.071%

    No Known Activations