© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105092
    Prev
    Next
    INDEX
    Explanations

    professors and leaders

    np_acts-logits-general · gemini-2.5-flash-lite

    commonly cited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     باستخدام
    0.49
     காலத்தில்
    0.47
     છે
    0.47
    বর্তী
    0.45
     ܗ
    0.44
    ilität
    0.44
     auprès
    0.43
     към
    0.41
     பயிற்சி
    0.41
     அடிகள்
    0.41
    POSITIVE LOGITS
     mehrere
    0.45
     oli
    0.45
     Terrain
    0.44
    \".
    0.43
    '
    0.43
     creature
    0.43
     operation
    0.42
     spor
    0.42
    !\!\
    0.41
     sann
    0.41
    Activations Density 0.000%

    No Known Activations