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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12432
    Prev
    Next
    INDEX
    Explanations

    types of products and activities

    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_16k_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
     productColor
    0.52
     digestive
    0.50
    <unused985>
    0.47
     pSig
    0.46
     decadent
    0.46
     hairstyle
    0.46
     mucosal
    0.46
     enzymatic
    0.46
     产品
    0.44
     hematopoietic
    0.44
    POSITIVE LOGITS
    www
    0.57
    2
    0.52
    1
    0.52
    For
    0.51
    Z
    0.50
    x
    0.49
    Last
    0.48
    H
    0.48
    L
    0.48
    <
    0.48
    Activations Density 0.008%

    No Known Activations