© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 306
    Prev
    Next
    INDEX
    Explanations

    . followed by g

    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
    兮
    0.86
    arele
    0.75
     dy
    0.66
    urring
    0.65
     wik
    0.64
    ources
    0.64
     roten
    0.64
    itud
    0.64
    ibility
    0.63
     leia
    0.62
    POSITIVE LOGITS
    C
    1.46
    S
    1.30
    D
    1.25
    E
    1.24
    A
    1.22
     vivos
    1.18
    P
    1.11
    R
    1.10
    M
    1.09
    💈
    1.09
    Activations Density 2.281%

    No Known Activations