© 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. 73192
    Prev
    Next
    INDEX
    Explanations

    . Bank. hopper. Black. placed. limited

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

    wanting something from others

    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
    ція
    0.48
    新生
    0.47
    後
    0.46
    quent
    0.46
    盐
    0.46
    連
    0.45
    電
    0.45
    聯
    0.44
    лав
    0.43
    缓
    0.43
    POSITIVE LOGITS
    ERA
    0.53
     çıkart
    0.47
    ENTO
    0.47
     misty
    0.46
     alquiler
    0.46
    UKI
    0.46
     çıkarm
    0.46
     kıl
    0.45
     jit
    0.44
    agar
    0.44
    Activations Density 0.000%

    No Known Activations