© 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. 26119
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    TextBoxColumn
    -0.91
    Dll
    -0.90
    UserDefaults
    -0.88
    ématiques
    -0.86
     listop
    -0.86
    ||}
    -0.86
     manchmal
    -0.85
    崩壊
    -0.85
     surpren
    -0.85
     noviembre
    -0.83
    POSITIVE LOGITS
    </b>
    0.95
     according
    0.88
     largely
    0.85
     commenti
    0.85
    according
    0.84
    Incoming
    0.84
    âteau
    0.82
    нен
    0.82
    Activité
    0.80
    vo
    0.80
    Activations Density 0.002%

    No Known Activations