Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 567
    Prev
    Next
    INDEX
    Explanations

    news sources and urls

    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
    жом
    0.21
    Substring
    0.21
    ປະກອບ
    0.20
     হাসানের
    0.20
    ান্তরে
    0.20
    损
    0.20
     בין
    0.20
     Pflanzen
    0.20
    ِمض
    0.19
    科研
    0.19
    POSITIVE LOGITS
    ''
    0.23
    ta
    0.22
     whopping
    0.22
     cools
    0.22
    %)
    0.21
    ಕೂ
    0.21
     NGO
    0.20
    ose
    0.20
    ii
    0.20
     খুবই
    0.20
    Activations Density 0.004%

    No Known Activations