© 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. 183937
    Prev
    Next
    INDEX
    Explanations

    equal reduction

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

    IP address and map information

    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
    :
    0.49
    做法
    0.46
    📅
    0.45
     борь
    0.44
    宣言
    0.44
     BASED
    0.44
    ˖
    0.44
    v
    0.43
     kdo
    0.43
    ;
    0.43
    POSITIVE LOGITS
     রাধানাথ
    0.47
    ogast
    0.46
    CipherText
    0.44
     Aufnahme
    0.44
     Oncol
    0.44
    ackbar
    0.43
    ostar
    0.42
     ハン
    0.41
     hepatic
    0.41
     Hispan
    0.41
    Activations Density 0.000%

    No Known Activations