© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5567
    Prev
    Next
    INDEX
    Explanations

    extracted from provided text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ajah
    1.84
    swf
    1.76
    ндарт
    1.65
    jera
    1.64
     basada
    1.62
    ','%
    1.61
     especializada
    1.61
    oop
    1.59
     enfoc
    1.59
    踵
    1.58
    POSITIVE LOGITS
    itement
    0.93
    ırmak
    0.92
     conto
    0.90
    ɯ
    0.85
    꺼
    0.82
    ITATE
    0.81
    unnumbered
    0.80
    lord
    0.80
     begs
    0.79
     veryvery
    0.79
    Activations Density 0.012%

    No Known Activations