© 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. 189274
    Prev
    Next
    INDEX
    Explanations

    lists of itemsowner, location, or activity

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

    whether residents

    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
     Gets
    0.55
     a
    0.50
    漆
    0.48
     mentor
    0.48
     Pyro
    0.47
    Ƒ
    0.46
     Gives
    0.46
    সাথে
    0.46
    漠
    0.45
     Denne
    0.44
    POSITIVE LOGITS
     exclusivement
    0.55
    wać
    0.51
     expansión
    0.50
     ስርዓ
    0.48
    ptir
    0.47
    ávají
    0.46
    etically
    0.46
    ło
    0.45
    cić
    0.45
     شار
    0.45
    Activations Density 0.000%

    No Known Activations