© 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. 16-GEMMASCOPE-2-RES-16K
    7. 414
    Prev
    Next
    INDEX
    Explanations

    Hebrew letters י and ו

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

    astrology and astronomy

    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_16_width_16k_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
    6
    0.82
    9
    0.79
    5
    0.76
    4
    0.75
    8
    0.72
    3
    0.68
    یم
    0.66
    7
    0.64
    =(
    0.64
    ります
    0.64
    POSITIVE LOGITS
    ي
    0.87
    z
    0.82
    <unused411>
    0.80
    <unused514>
    0.80
    ו
    0.79
    י
    0.79
    <unused626>
    0.79
    و
    0.78
    <unused365>
    0.78
    <unused455>
    0.78
    Activations Density 0.184%

    No Known Activations