© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21995
    Prev
    Next
    INDEX
    Explanations

    founded on, job with, starting from, grilled cheese

    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_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
     모든
    0.44
     όλ
    0.42
    NaOMe
    0.42
    단
    0.42
    VEN
    0.41
    也
    0.41
    Palindrome
    0.40
    HPV
    0.40
     لكل
    0.39
    List
    0.39
    POSITIVE LOGITS
     Americans
    0.50
     America
    0.44
    कीस
    0.44
     Soviet
    0.44
     ayudar
    0.43
    '
    0.43
     Amerika
    0.42
     Democratic
    0.42
     Squadron
    0.42
     reinforcements
    0.42
    Activations Density 0.002%

    No Known Activations