© 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. 37245
    Prev
    Next
    INDEX
    Explanations

    usually

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

    representations closer together

    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
     powering
    0.39
    iced
    0.38
     unsatisfactory
    0.37
    蛄
    0.37
    ্যে
    0.36
     playground
    0.36
    creational
    0.36
    Dice
    0.36
    創
    0.35
     seaside
    0.35
    POSITIVE LOGITS
     обычно
    0.68
     সাধারণত
    0.68
     عادة
    0.66
     biasanya
    0.65
     보통
    0.64
     usually
    0.63
     genellikle
    0.62
    usually
    0.62
     geralmente
    0.60
     normalerweise
    0.60
    Activations Density 0.042%

    No Known Activations