© 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. 19026
    Prev
    Next
    INDEX
    Explanations

    we are taking

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

    conditional statements and returns

    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
     כל
    0.44
    ❺
    0.44
    י
    0.43
    名稱
    0.43
    ③
    0.43
     ваши
    0.42
    YOUR
    0.42
    ר
    0.42
    א
    0.42
    դ
    0.41
    POSITIVE LOGITS
     hasn
    0.51
     tenemos
    0.51
     continuamos
    0.51
     kita
    0.51
     tivemos
    0.51
     abbiamo
    0.50
     belum
    0.48
     máme
    0.48
     dobbiamo
    0.48
     temos
    0.47
    Activations Density 0.002%

    No Known Activations