© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    confirmation prompts

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

    error, status, or user command

    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
    上也
    0.39
    NAMEN
    0.37
     patitth
    0.37
    ៥
    0.37
    VEN
    0.37
    RELATIVA
    0.36
     பிள்ள
    0.36
    ៤
    0.35
     unmittelbar
    0.35
    ៦
    0.34
    POSITIVE LOGITS
     your
    0.54
     you
    0.54
     requested
    0.47
     você
    0.44
     bạn
    0.44
     Hello
    0.44
     recieved
    0.44
     inputted
    0.44
     #{
    0.42
    !");
    0.41
    Activations Density 0.006%

    No Known Activations