© 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. 224313
    Prev
    Next
    INDEX
    Explanations

    daily basis

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

    structure and routine

    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
    "+"
    0.48
    <0xE3>
    0.46
    Sharing
    0.45
    Winning
    0.45
    \\\\
    0.45
    as
    0.44
    the
    0.44
    winner
    0.43
    Unsere
    0.43
    와
    0.43
    POSITIVE LOGITS
     منذ
    0.52
     अतीत
    0.49
     چک
    0.48
     comerci
    0.47
     सप्त
    0.46
     acknowled
    0.45
     चढ़
    0.45
     निकासी
    0.45
     विरोध
    0.45
     आवृत्ति
    0.45
    Activations Density 0.000%

    No Known Activations