© 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. 173293
    Prev
    Next
    INDEX
    Explanations

    legal or business contexts

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

    look for

    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
    𒈬
    0.56
    负责人
    0.54
     negativa
    0.52
     öğrenciler
    0.52
     мини
    0.51
     प्रोज
    0.51
     gên
    0.50
    даря
    0.50
     проблема
    0.50
    ະພັນ
    0.50
    POSITIVE LOGITS
    k
    0.50
    tl
    0.49
    TL
    0.47
    fb
    0.47
    bottom
    0.45
     Ordinance
    0.44
    SC
    0.44
    rate
    0.44
    htt
    0.43
    ttl
    0.42
    Activations Density 0.000%

    No Known Activations