© 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. 89082
    Prev
    Next
    INDEX
    Explanations

    specific phrases following certain words

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

    questions about

    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
    \
    0.56
     xếp
    0.55
     /(\
    0.55
     Squirrel
    0.54
     ແມ່ນ
    0.53
     Prä
    0.52
     റാ
    0.51
     Hồ
    0.51
    \,\
    0.50
     katıl
    0.50
    POSITIVE LOGITS
    ن
    0.66
    น
    0.60
    ش
    0.58
    س
    0.57
    ส
    0.50
    า
    0.50
    レ
    0.50
    ስ
    0.49
    ORUS
    0.49
    ل
    0.48
    Activations Density 0.000%

    No Known Activations