© 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. 79766
    Prev
    Next
    INDEX
    Explanations

    inside 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_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
    л
    0.49
    !",
    0.49
    ,",
    0.49
    "!
    0.48
    е
    0.48
    Across
    0.48
    ل
    0.48
    λ
    0.46
    ...",
    0.46
    ન
    0.46
    POSITIVE LOGITS
     fable
    0.46
     evalu
    0.46
     mappa
    0.44
     fuller
    0.43
     صالح
    0.43
     돌아
    0.43
     bior
    0.42
     hyg
    0.42
     מלא
    0.42
     fluency
    0.42
    Activations Density 0.004%

    No Known Activations