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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5808
    Prev
    Next
    INDEX
    Explanations

    what and why questions

    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
    க
    0.46
    Та
    0.46
     цик
    0.45
    ि
    0.45
    сі
    0.44
    但
    0.44
    ك
    0.43
     тыс
    0.43
    Т
    0.43
    мет
    0.43
    POSITIVE LOGITS
     AppCompat
    0.46
    SSON
    0.44
    Assessment
    0.43
    Chemistry
    0.43
    Establish
    0.42
    establish
    0.41
     Giang
    0.41
     gauge
    0.40
    sender
    0.40
    Warehouse
    0.40
    Activations Density 0.020%

    No Known Activations