© 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. 15648
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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
    Ώ
    -0.88
     recomendada
    -0.88
    rapper
    -0.87
    iseks
    -0.85
    فیلم
    -0.83
    Materiál
    -0.83
     corporativa
    -0.82
     ۱۴۰۰
    -0.82
     combustível
    -0.82
     informazioni
    -0.82
    POSITIVE LOGITS
     carlo
    1.02
     teresa
    0.96
     Sinf
    0.96
    boldsymbol
    0.93
    今でも
    0.93
     Græ
    0.93
     Abon
    0.92
    画像は
    0.91
     eighth
    0.90
     milano
    0.90
    Activations Density 0.004%

    No Known Activations