© 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. 128858
    Prev
    Next
    INDEX
    Explanations

    introductory words or conjunctions

    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
    ส
    0.51
    AZ
    0.46
     Madras
    0.46
    Atm
    0.45
    +
    0.45
    담
    0.45
     apparence
    0.45
     Gourmet
    0.44
    娍
    0.43
     Armen
    0.43
    POSITIVE LOGITS
     benchmarking
    0.51
     lifts
    0.47
     offsets
    0.47
     benchmarks
    0.46
     implements
    0.46
    的東西
    0.45
     renders
    0.44
    ığında
    0.43
     ["
    0.43
     benutzt
    0.43
    Activations Density 0.005%

    No Known Activations