© 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. 149242
    Prev
    Next
    INDEX
    Explanations

    interrogated suspects, Twin bed, local community

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

    SELECT count(*)

    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
     alight
    0.50
     đột
    0.50
     combust
    0.48
     dạng
    0.48
     swollen
    0.47
    ોર્
    0.46
     cứ
    0.46
    )^{[\
    0.45
     technologically
    0.45
     kiểu
    0.45
    POSITIVE LOGITS
    ümüş
    0.46
    ual
    0.45
    SA
    0.45
    amus
    0.44
    ella
    0.44
    ueto
    0.43
    ital
    0.42
    amon
    0.42
    emann
    0.42
    -<
    0.42
    Activations Density 0.000%

    No Known Activations