© 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. 65916
    Prev
    Next
    INDEX
    Explanations

    conditional checks in code

    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
     confé
    -1.06
     also
    -1.00
    oiseau
    -0.89
    efined
    -0.86
    carol
    -0.86
     también
    -0.85
    感じで
    -0.84
     more
    -0.82
     paño
    -0.82
     better
    -0.81
    POSITIVE LOGITS
    Spec
    0.89
    าสตร์
    0.89
    ."'
    0.89
    ке
    0.88
     californ
    0.86
     Latter
    0.86
    IGNS
    0.85
     qualquer
    0.85
     juuri
    0.85
     это
    0.85
    Activations Density 0.006%

    No Known Activations