© 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. 241878
    Prev
    Next
    INDEX
    Explanations

    skills, personal requirements

    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
     ܠ
    0.55
     granting
    0.49
    ilded
    0.49
     ा
    0.48
     آپریشن
    0.47
    ܀
    0.47
     effectuées
    0.46
    ጐ
    0.46
     appraised
    0.46
     investigated
    0.45
    POSITIVE LOGITS
    \
    0.48
     tiny
    0.47
     Xiang
    0.46
     přip
    0.46
    _{
    0.45
     הצ
    0.44
    n
    0.44
    {~
    0.44
    (
    0.44
    Transform
    0.44
    Activations Density 0.001%

    No Known Activations