© 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. 48913
    Prev
    Next
    INDEX
    Explanations

    benefit plans

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

    relationships and connections

    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
    sa
    0.45
     [§
    0.45
    ur
    0.44
     العد
    0.44
     esteem
    0.44
     ew
    0.44
     nextline
    0.44
     Workshops
    0.43
    your
    0.43
    YOUR
    0.43
    POSITIVE LOGITS
    ंकज
    0.52
    嘶
    0.51
    扫描
    0.48
    ายเป็น
    0.47
    aiman
    0.47
    ીએ
    0.47
     Peralta
    0.45
    絓
    0.45
    ってる
    0.44
     spettac
    0.44
    Activations Density 0.000%

    No Known Activations