© 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. 15-GEMMASCOPE-2-RES-16K
    7. 5056
    Prev
    Next
    INDEX
    Explanations

    button click

    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
     Spectrum
    1.43
     Choice
    1.36
     Trident
    1.32
    Spectrum
    1.28
     Фили
    1.26
    PORT
    1.20
    }-(\
    1.20
    ﺋ
    1.20
     Habib
    1.19
     Restricted
    1.18
    POSITIVE LOGITS
     rendus
    1.18
    ContentLoaded
    1.14
     sucedido
    1.14
     recharged
    1.12
     urod
    1.12
    akkam
    1.12
    ceptions
    1.12
    addling
    1.11
    mounted
    1.10
     onLoad
    1.09
    Activations Density 0.020%

    No Known Activations