© 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. 26800
    Prev
    Next
    INDEX
    Explanations

    Pas

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

    following specified tokens

    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
     이유
    0.44
     berasal
    0.43
     외부
    0.42
    幣
    0.41
    አ
    0.40
     앞
    0.40
     왜
    0.40
     마음
    0.40
     육
    0.39
    시아
    0.38
    POSITIVE LOGITS
     كلكم
    0.44
     Tuition
    0.42
     Scrooge
    0.40
    epis
    0.39
     عندي
    0.39
    engineer
    0.39
     youll
    0.39
    achelor
    0.39
    instal
    0.39
     Pelham
    0.39
    Activations Density 0.003%

    No Known Activations