© 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. 132939
    Prev
    Next
    INDEX
    Explanations

    Prof

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

    this thing

    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
     depositions
    0.46
     त्यांनी
    0.45
    ப்பட்டன
    0.44
     ß
    0.44
     consultancy
    0.44
     Rwandan
    0.44
     നടത്തിയ
    0.42
     он
    0.42
     Rwanda
    0.42
    了他
    0.41
    POSITIVE LOGITS
    i
    0.56
    يلا
    0.47
    底
    0.45
    某个
    0.45
    Turn
    0.44
    Friendly
    0.44
    Ex
    0.43
    Bounce
    0.43
     Kabhi
    0.43
    就是一个
    0.43
    Activations Density 0.000%

    No Known Activations