© 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. 195808
    Prev
    Next
    INDEX
    Explanations

    By taking or liberating

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

    minerals and searching

    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
     noticias
    0.49
    he
    0.46
    \
    0.44
     their
    0.44
    political
    0.44
     noticia
    0.43
    vt
    0.43
     políticos
    0.43
     prepayment
    0.43
    usa
    0.42
    POSITIVE LOGITS
     ಮೂಲ
    0.50
     প্রতিষ্ঠিত
    0.49
     ಹಿಂದ
    0.49
     ξε
    0.49
     rivulet
    0.48
     δ
    0.48
     ಹಲವಾರು
    0.47
     ബാറ്റ
    0.47
    oscope
    0.46
     ಅನೇಕ
    0.46
    Activations Density 0.000%

    No Known Activations