© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 225914
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating possession or accompaniment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getActive
    0.52
    ρού
    0.46
     by
    0.46
    व
    0.46
    泹
    0.44
    жается
    0.43
    ItemBackground
    0.43
    тера
    0.43
    時
    0.43
    лке
    0.42
    POSITIVE LOGITS
    に関する法律
    0.48
     scriv
    0.48
     defamation
    0.47
     allegory
    0.46
     smith
    0.46
     convey
    0.45
     dyslex
    0.45
     Nacional
    0.45
     amicable
    0.44
    Swedish
    0.44
    Activations Density 0.001%

    No Known Activations