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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12432
    Prev
    Next
    INDEX
    Explanations

    introductory words

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     productColor
    0.55
     tensors
    0.51
    Соцмережа
    0.50
     oraș
    0.48
     decadent
    0.48
     manglid
    0.48
     stateMutability
    0.48
    <unused985>
    0.48
     食品
    0.47
     pSig
    0.47
    POSITIVE LOGITS
    2
    0.57
    www
    0.55
    <
    0.53
    DC
    0.52
    Last
    0.50
    For
    0.49
    point
    0.47
    ↵
    0.47
    New
    0.47
    <0xE2>
    0.47
    Activations Density 0.017%

    No Known Activations