© 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. 128568
    Prev
    Next
    INDEX
    Explanations

    URL `action` or `index`

    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
     классов
    -1.17
     komik
    -1.14
     there
    -1.11
     Garantía
    -1.09
    UrlHelper
    -1.07
    ύ
    -1.07
     étui
    -1.06
     alcanzó
    -1.05
     tambien
    -1.05
     två
    -1.05
    POSITIVE LOGITS
    get
    1.12
    </em>
    1.08
     view
    1.02
     get
    1.02
     Vise
    0.97
     eeuw
    0.96
    钦
    0.95
     at
    0.94
    ecé
    0.93
     or
    0.93
    Activations Density 0.008%

    No Known Activations