© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5207
    Prev
    Next
    INDEX
    Explanations

    takes two arguments

    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_12_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
    忡
    1.81
     cruised
    1.76
     DJI
    1.73
     caminh
    1.71
    炁
    1.67
     senjata
    1.63
     보니
    1.62
     Tripathi
    1.61
     munic
    1.60
     trầm
    1.59
    POSITIVE LOGITS
    角
    2.09
    tang
    2.05
     oed
    1.99
    l
    1.96
     epitopes
    1.94
    uette
    1.90
    stag
    1.85
    r
    1.85
    rams
    1.83
    u
    1.81
    Activations Density 0.002%

    No Known Activations