© 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. 120543
    Prev
    Next
    INDEX
    Explanations

    credit, elements, like, polarity

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

    specific formatting or structure

    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
    त्त
    0.45
    ’
    0.45
     Sunderland
    0.44
    的問題
    0.44
    ปลอดภัย
    0.43
     problemi
    0.43
     paranormal
    0.43
     psychiatric
    0.42
    டன்
    0.42
     त
    0.42
    POSITIVE LOGITS
     tissus
    0.46
    amam
    0.45
     racines
    0.45
     suas
    0.44
     cacao
    0.44
    úz
    0.44
    rouge
    0.44
    শস্ত্র
    0.43
    ítica
    0.43
    fiscal
    0.43
    Activations Density 0.001%

    No Known Activations