© 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. 227147
    Prev
    Next
    INDEX
    Explanations

    make the

    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
     преимущества
    0.49
    );\
    0.47
    Ꮶ
    0.43
     начала
    0.43
    ).”
    0.42
     заместитель
    0.42
     круг
    0.42
     явления
    0.42
    역시
    0.41
     כמה
    0.41
    POSITIVE LOGITS
    im
    0.57
     befol
    0.48
     outbreaks
    0.46
     layouts
    0.45
     syscall
    0.44
    ر
    0.44
    webhook
    0.44
    濯
    0.44
    ح
    0.43
     Attack
    0.43
    Activations Density 0.001%

    No Known Activations