© 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. 106191
    Prev
    Next
    INDEX
    Explanations

    non-english characters and numbers

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

    cause, effect, or resulting conditions

    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
     ó
    0.50
     intrav
    0.48
     couper
    0.46
     damaging
    0.46
     desactiv
    0.46
    损害
    0.46
     CharPtr
    0.45
     clamp
    0.45
     emerald
    0.44
    生育
    0.44
    POSITIVE LOGITS
    rofoam
    0.47
    Ś
    0.46
    ारों
    0.45
    نق
    0.45
    inis
    0.45
    Ordinate
    0.45
    appings
    0.45
    ettek
    0.45
    apost
    0.44
    enb
    0.43
    Activations Density 0.000%

    No Known Activations