© 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-65K
    7. 62250
    Prev
    Next
    INDEX
    Explanations

    comparisons of size and performance

    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
     kahe
    0.54
    この
    0.50
    தியும்
    0.49
     samym
    0.47
     آباد
    0.46
     Eigenschaften
    0.46
    南
    0.45
    鲳
    0.44
    ந்தை
    0.44
     siis
    0.43
    POSITIVE LOGITS
    your
    0.54
     ваших
    0.54
     than
    0.52
     ਤੁਹਾ
    0.49
     your
    0.49
    you
    0.49
     вашем
    0.48
     votre
    0.48
    telling
    0.47
     عندما
    0.46
    Activations Density 0.005%

    No Known Activations