© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47353
    Prev
    Next
    INDEX
    Explanations

    phrases following "in", "of", "with"

    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
     suspensions
    0.46
     deserts
    0.45
    सूची
    0.43
     compromises
    0.43
    越
    0.42
     protege
    0.42
    莲
    0.42
     orchids
    0.41
    ysk
    0.41
    ieniu
    0.41
    POSITIVE LOGITS
     י
    0.43
     אפ
    0.43
    സു
    0.41
     কীট
    0.41
    InterfaceLine
    0.41
     homomorphism
    0.41
     hük
    0.40
    urlString
    0.40
     ഈ
    0.40
    criar
    0.40
    Activations Density 0.009%

    No Known Activations