© 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. 110534
    Prev
    Next
    INDEX
    Explanations

    culture and models

    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
     жерт
    0.61
     ombil
    0.54
     только
    0.52
     виртуа
    0.52
     толькі
    0.51
    ᠨ
    0.51
     этот
    0.50
    㚘
    0.50
    ुक्त
    0.49
     महिला
    0.49
    POSITIVE LOGITS
     =
    0.46
     shipping
    0.44
     disease
    0.41
    ding
    0.40
     turnout
    0.39
    arrerol
    0.38
    dist
    0.38
    OA
    0.37
    Les
    0.37
     Samoa
    0.37
    Activations Density 0.006%

    No Known Activations