© 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. 20932
    Prev
    Next
    INDEX
    Explanations

    looking for

    np_acts-logits-general · gemini-2.5-flash-lite

    discuss the

    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
     U
    0.52
     Id
    0.45
     Love
    0.42
     Pm
    0.42
     الهدف
    0.42
     Obama
    0.41
     Yar
    0.40
    我很
    0.40
     param
    0.40
    fly
    0.40
    POSITIVE LOGITS
     abiotic
    0.43
    шаем
    0.43
    roits
    0.42
    轵
    0.39
    evole
    0.39
     abstractions
    0.38
    ہے
    0.38
    prits
    0.38
     barbit
    0.38
    assic
    0.38
    Activations Density 0.006%

    No Known Activations