© 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. 34-GEMMASCOPE-RES-131K
    7. 58290
    Prev
    Next
    INDEX
    Explanations

    within a timeframe

    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_34/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
    SystemColors
    -0.83
    ronyms
    -0.83
    mata
    -0.81
     Ở
    -0.81
     ở
    -0.81
    ucie
    -0.79
    kező
    -0.78
    после
    -0.76
    iera
    -0.75
    غيل
    -0.75
    POSITIVE LOGITS
     within
    9.13
    Within
    6.66
    within
    6.66
     Within
    6.34
     dentro
    6.00
     innerhalb
    5.94
     WITHIN
    5.31
     binnen
    5.09
    ภายใน
    4.63
    Dentro
    4.38
    Activations Density 1.061%

    No Known Activations