© 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. 16-GEMMASCOPE-2-RES-16K
    7. 425
    Prev
    Next
    INDEX
    Explanations

    prefix characters like %, \, ►

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

    extends State

    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_16_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
     The
    0.93
     and
    0.93
    E
    0.89
    A
    0.88
     was
    0.86
    ,
    0.83
    O
    0.82
    Ì
    0.82
    I
    0.81
    U
    0.81
    POSITIVE LOGITS
    s
    1.02
    ти
    0.81
     مرتبط
    0.80
    "。
    0.77
     sasane
    0.77
    liğini
    0.76
    לות
    0.75
     非
    0.75
    dengan
    0.75
    ский
    0.74
    Activations Density 0.114%

    No Known Activations