© 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. 166003
    Prev
    Next
    INDEX
    Explanations

    this the

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

    code and coordinates

    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
     Yeshu
    0.52
     memoirs
    0.50
     cruelty
    0.48
    сини
    0.46
     ძალი
    0.44
    رین
    0.44
     흰
    0.44
    残酷
    0.43
     variants
    0.43
     prerog
    0.43
    POSITIVE LOGITS
     कटा
    0.48
    živ
    0.46
    southeast
    0.44
    cluded
    0.44
    Katie
    0.44
    ၀
    0.43
     '
    0.42
    Including
    0.42
    south
    0.42
    Alk
    0.42
    Activations Density 0.001%

    No Known Activations