© 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. 76560
    Prev
    Next
    INDEX
    Explanations

    financial and technical phrasing

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

    common word followed by another common word

    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
    罘
    0.47
    沒
    0.47
    يا
    0.47
     نہیں
    0.47
    ั่ว
    0.47
     yanı
    0.46
    髌
    0.46
     хви
    0.45
    ،
    0.45
    POSITIVE LOGITS
    <unused664>
    0.43
     imo
    0.41
    <unused681>
    0.41
    អេឡិចត្រូនិច
    0.41
     iPod
    0.41
    roud
    0.40
     bezier
    0.40
     EBITDA
    0.40
     finan
    0.39
    estellten
    0.39
    Activations Density 0.002%

    No Known Activations