© 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. 191466
    Prev
    Next
    INDEX
    Explanations

    first hints of

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

    female teacher, future information, systemic inflammation, windows updates

    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
    窮
    0.49
    槌
    0.46
    籠
    0.45
     உலோக
    0.44
     Mesopot
    0.43
     قات
    0.43
     الشمس
    0.43
    াহিয়া
    0.42
     ሂደ
    0.41
     thorax
    0.41
    POSITIVE LOGITS
     ======
    0.45
     akibat
    0.45
     प्रद
    0.45
     जीतकर
    0.44
     इन्वेस्टमेंट
    0.44
     resultante
    0.44
    mck
    0.44
     overwritten
    0.43
     inwest
    0.43
    のである
    0.43
    Activations Density 0.000%

    No Known Activations