© 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. 145160
    Prev
    Next
    INDEX
    Explanations

    flashest flyer

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

    marketing copy about new things

    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
     fondamental
    0.52
     yoğun
    0.48
     McGuire
    0.43
     THREE
    0.43
     réfléch
    0.42
    ジム
    0.42
     thử
    0.42
    飪
    0.42
     Stories
    0.41
    ത്തു
    0.41
    POSITIVE LOGITS
    Automat
    0.44
    뭣
    0.44
     자동
    0.42
    娛樂
    0.42
    telegram
    0.40
     احمد
    0.40
    oggetto
    0.40
    ॉफ्ट
    0.40
    örg
    0.40
    ONG
    0.40
    Activations Density 0.001%

    No Known Activations