© 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. 160804
    Prev
    Next
    INDEX
    Explanations

    contractual or Shi. US SEC

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

    backhanded compliments

    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
    加坡
    0.50
    无论是
    0.49
    ᒻ
    0.46
    音乐
    0.46
    装修
    0.46
     handcrafted
    0.46
    кви
    0.44
    自从
    0.44
    ?
    0.44
     philanthropic
    0.43
    POSITIVE LOGITS
    nite
    0.58
    pal
    0.54
    dung
    0.54
    im
    0.53
    pictures
    0.50
    dwelling
    0.50
    lips
    0.49
    ildet
    0.49
    nun
    0.48
    mul
    0.48
    Activations Density 0.000%

    No Known Activations