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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32401
    Prev
    Next
    INDEX
    Explanations

    Instagram stories anonymously

    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_16_width_262k_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
    𝐬
    0.63
     ​​
    0.59
     portátil
    0.58
     triathlon
    0.58
     xpath
    0.57
    aschen
    0.57
     wówczas
    0.57
    짱
    0.57
     EVs
    0.56
     conducción
    0.56
    POSITIVE LOGITS
    |
    0.61
    idoscope
    0.51
    {
    0.50
    W
    0.50
    SCHOOL
    0.49
     "|
    0.49
    <h4>
    0.49
     impair
    0.48
    ,|
    0.48
    堬
    0.47
    Activations Density 0.003%

    No Known Activations