© 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. 4713
    Prev
    Next
    INDEX
    Explanations

    data

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

    data and datasets

    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
     vardır
    0.58
    语气
    0.53
    讨厌
    0.53
     leçon
    0.53
     hatırl
    0.52
    盉
    0.52
    反对
    0.51
     comical
    0.51
    轵
    0.51
     eğer
    0.51
    POSITIVE LOGITS
     data
    1.52
     datasets
    1.44
    data
    1.40
     dataset
    1.29
     Data
    1.20
     database
    1.20
    dataset
    1.16
     databases
    1.16
     DATA
    1.13
    データ
    1.08
    Activations Density 0.397%

    No Known Activations