© 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. 142207
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

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

    represents a

    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
    څ
    0.45
    cios
    0.44
    ייט
    0.44
    akings
    0.43
    これから
    0.43
    enciais
    0.43
     कार्यकर्त्या
    0.42
     ವರ್
    0.42
    тельными
    0.42
    cektir
    0.42
    POSITIVE LOGITS
     y
    0.54
     six
    0.48
     of
    0.48
     d
    0.48
     medicine
    0.48
     stoppage
    0.48
     Medicine
    0.47
     медици
    0.47
     Meteorological
    0.47
    Name
    0.47
    Activations Density 0.000%

    No Known Activations