© 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. 240867
    Prev
    Next
    INDEX
    Explanations

    highest population

    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
     integrante
    0.58
     cristiana
    0.49
     객
    0.48
     murm
    0.47
     miembros
    0.47
     えっ
    0.47
     IOError
    0.47
     afectadas
    0.47
     escuch
    0.46
     eficacia
    0.46
    POSITIVE LOGITS
    青年
    0.54
    نام
    0.53
    Politics
    0.48
    TEL
    0.46
    政治
    0.45
    燉
    0.45
    тел
    0.44
     Politics
    0.44
     Entertain
    0.44
    展
    0.44
    Activations Density 0.001%

    No Known Activations