© 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. 163355
    Prev
    Next
    INDEX
    Explanations

    post office

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

    progressive overload training

    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
    พี
    0.44
     松
    0.43
     deserts
    0.43
     crosses
    0.43
     є
    0.42
     Mapper
    0.42
    eds
    0.41
     αφ
    0.41
    𝗽
    0.41
     Maeda
    0.40
    POSITIVE LOGITS
    WOM
    0.46
     WOM
    0.45
     presion
    0.44
     كنت
    0.44
     ولم
    0.43
     Mujeres
    0.43
     குழந்த
    0.43
     حالة
    0.43
    oblig
    0.43
     верхней
    0.43
    Activations Density 0.001%

    No Known Activations