© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215132
    Prev
    Next
    INDEX
    Explanations

    example usage

    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_40_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
     coû
    0.40
     Projek
    0.40
     会
    0.39
    षण
    0.39
    زء
    0.39
     difficoltà
    0.39
     Pä
    0.38
    会
    0.38
     गड्
    0.38
    猀
    0.38
    POSITIVE LOGITS
    Cu
    0.36
    NV
    0.35
     نثر
    0.35
     readership
    0.35
    uran
    0.35
     extingu
    0.35
    }`}
    0.34
     metal
    0.34
    ected
    0.34
     পুত্রের
    0.34
    Activations Density 0.002%

    No Known Activations