© 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. 62055
    Prev
    Next
    INDEX
    Explanations

    publishers and entities

    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
    文學
    0.46
     Linguistic
    0.41
     ഭാ
    0.41
     |,
    0.40
     `:`,
    0.39
     récente
    0.39
     récemment
    0.39
     літера
    0.39
     :',
    0.39
     subalgebra
    0.38
    POSITIVE LOGITS
    SD
    0.49
    Household
    0.44
    FOM
    0.43
     households
    0.41
    dfunding
    0.41
     household
    0.41
    CustomerID
    0.40
    Duz
    0.40
    sd
    0.39
    প্তাহ
    0.39
    Activations Density 0.009%

    No Known Activations