© 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. 197563
    Prev
    Next
    INDEX
    Explanations

    innovative, fewer, avoiding, discover

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

    certainly not, sometimes lead

    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
     لیګ
    0.45
     꾸
    0.44
    グラフ
    0.44
    ocap
    0.44
    경상
    0.44
     प्रथा
    0.43
    itik
    0.43
     परिश
    0.43
    epage
    0.42
     संथाल
    0.42
    POSITIVE LOGITS
    😲
    0.45
    Done
    0.43
     energi
    0.43
    सिर
    0.42
    🤯
    0.42
     clues
    0.42
     subsidiaries
    0.42
    m
    0.41
    :{
    0.41
     Done
    0.41
    Activations Density 0.001%

    No Known Activations