© 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. 26254
    Prev
    Next
    INDEX
    Explanations

    prison and resources

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

    R groups in chemistry

    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
    ўкі
    0.97
    літы
    0.96
     Расійскай
    0.93
    скіх
    0.89
    Архі
    0.88
     клі
    0.87
    ліза
    0.86
    Კ
    0.86
    Під
    0.84
    краё
    0.84
    POSITIVE LOGITS
     Đ
    1.16
     đ
    1.15
     trong
    1.14
     Công
    1.09
     Phương
    1.09
     Văn
    1.09
     nguyên
    1.07
     Trung
    1.07
     khi
    1.06
     mới
    1.06
    Activations Density 0.000%

    No Known Activations