© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13812
    Prev
    Next
    INDEX
    Explanations

    I am, I try, I hope, we are

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

    I can, I want, I have

    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_16k_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
     for
    0.64
     lưu
    0.59
    맨
    0.59
    вати
    0.57
     ਤੁਹਾ
    0.56
    .
    0.54
     reasons
    0.54
     있지만
    0.54
     rejuvenation
    0.54
     remittance
    0.53
    POSITIVE LOGITS
     can
    0.80
    can
    0.65
     was
    0.64
     seleccione
    0.61
     knew
    0.60
     are
    0.60
    q
    0.59
    vgl
    0.59
    ks
    0.58
    brahim
    0.58
    Activations Density 1.148%

    No Known Activations