© 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-262K
    7. 83236
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific titles/concepts

    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
    jsonObject
    0.45
     هو
    0.42
    芠
    0.42
     хотят
    0.42
    ΗΣ
    0.41
     ໜອງ
    0.41
     quede
    0.39
     niego
    0.38
     veulent
    0.38
    करें
    0.38
    POSITIVE LOGITS
    ’.
    0.43
     Ř
    0.42
     ரீ
    0.42
    radas
    0.38
     Manual
    0.38
     dst
    0.37
     Assignments
    0.37
     Ä
    0.37
     ñ
    0.37
     M
    0.36
    Activations Density 0.000%

    No Known Activations