© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 137152
    Prev
    Next
    INDEX
    Explanations

    dangerous items or substances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    銆
    0.40
    ᱫ
    0.40
     天然
    0.38
     lawfully
    0.38
     బు
    0.38
    ZQ
    0.38
    全
    0.38
     اظهار
    0.37
     Inaug
    0.37
    一般
    0.36
    POSITIVE LOGITS
    ことに
    0.41
    टने
    0.38
     favore
    0.37
     cou
    0.37
     alguien
    0.37
     Küh
    0.37
    icionar
    0.36
    "</
    0.36
    镤
    0.36
    CharSequence
    0.35
    Activations Density 0.002%

    No Known Activations