© 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. 34759
    Prev
    Next
    INDEX
    Explanations

    then, after, finalize

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

    running a program

    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
    аны
    0.47
    isees
    0.46
    ict
    0.44
    "><!--
    0.44
     vengo
    0.42
    ilites
    0.42
     Uri
    0.41
    वंत
    0.41
    어
    0.41
    똥
    0.41
    POSITIVE LOGITS
     затем
    0.51
     এরপর
    0.49
     vervolgens
    0.47
     Final
    0.47
     Después
    0.46
    仕上げ
    0.46
     যু
    0.44
    បញ្ចប់
    0.44
     finalize
    0.43
     anschließend
    0.43
    Activations Density 0.000%

    No Known Activations