© 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. 30170
    Prev
    Next
    INDEX
    Explanations

    words followed by prepositions

    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
    :
    0.51
    *
    0.51
    шти
    0.45
    %
    0.42
    *-
    0.41
    $^
    0.41
    *\
    0.39
     "
    0.39
     dfs
    0.38
    /
    0.38
    POSITIVE LOGITS
    蛎
    0.50
     apakah
    0.49
     aspetti
    0.47
     Polaribacter
    0.46
    Foldout
    0.44
     contenidos
    0.43
    uales
    0.43
    alakip
    0.42
     اضافی
    0.42
     있어요
    0.42
    Activations Density 0.001%

    No Known Activations