© 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. 199965
    Prev
    Next
    INDEX
    Explanations

    when you, Gallery |, Code ., cameras allow

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

    while it seems counterintuitive

    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
     diffic
    0.48
    नाची
    0.45
    נים
    0.43
    или
    0.41
    <0x8B>
    0.41
    ल्टी
    0.41
    ৃত্তি
    0.41
    шите
    0.41
    分的
    0.40
     pouss
    0.40
    POSITIVE LOGITS
     এ
    0.48
     justifies
    0.47
    kde
    0.46
     DOES
    0.46
     pleads
    0.45
    5
    0.44
    4
    0.44
     অক্টো
    0.44
     anthracite
    0.44
    ides
    0.43
    Activations Density 0.000%

    No Known Activations