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. 20512
    Prev
    Next
    INDEX
    Explanations

    quantity or capacity needed

    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
     Raiders
    0.42
    >(</
    0.42
     короля
    0.41
     elke
    0.40
    唃
    0.40
    ⌚
    0.40
    ಳೆದ
    0.39
    컷
    0.39
     überhaupt
    0.38
     Rebels
    0.38
    POSITIVE LOGITS
     superficial
    0.40
     حيث
    0.39
    رم
    0.38
     feel
    0.38
     doping
    0.38
     prevailing
    0.38
     successive
    0.36
     troph
    0.36
     likely
    0.36
     jossa
    0.36
    Activations Density 0.001%

    No Known Activations