© 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. 6699
    Prev
    Next
    INDEX
    Explanations

    starting with "PaLM"

    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
    tir
    3.22
    dür
    3.08
    nya
    3.01
    こと
    2.95
    ために
    2.91
    ための
    2.84
    yaj
    2.77
    س
    2.76
    yel
    2.73
    yesi
    2.72
    POSITIVE LOGITS
    ekwondo
    2.01
    verage
    1.97
    irstyle
    1.89
    aldb
    1.81
    aliyet
    1.80
    aaaaaaaa
    1.76
    esthetic
    1.72
    aarr
    1.72
    ître
    1.66
    ffine
    1.66
    Activations Density 0.404%

    No Known Activations