© 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. 165123
    Prev
    Next
    INDEX
    Explanations

    technical and scientific definitions

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

    and lists

    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
    n
    0.48
    at
    0.44
    p
    0.44
     senate
    0.43
    nur
    0.43
    location
    0.42
     была
    0.42
    al
    0.41
     electorate
    0.41
     Padova
    0.41
    POSITIVE LOGITS
     தீ
    0.49
     змо
    0.48
    युक्त
    0.48
     증
    0.48
    /**
    0.47
    নিজ
    0.47
    ଭ
    0.47
     ciertos
    0.46
     unabhäng
    0.46
     necessari
    0.46
    Activations Density 0.001%

    No Known Activations