© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 64041
    Prev
    Next
    INDEX
    Explanations

    can provoke reactions

    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_31_width_65k_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
    يل
    0.45
    ختلف
    0.45
    ាហ
    0.45
    preprocess
    0.44
    రా
    0.43
    wählen
    0.43
    ዋል
    0.42
    輥
    0.42
    መሳሳይ
    0.42
     ulike
    0.42
    POSITIVE LOGITS
     (
    0.48
     матери
    0.48
     (=
    0.47
     ó
    0.46
     niezbęd
    0.46
     (<
    0.46
     człowieka
    0.46
     deodorant
    0.46
     }
    0.45
     очень
    0.45
    Activations Density 0.022%

    No Known Activations