© 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. 5360
    Prev
    Next
    INDEX
    Explanations

    request to provide information

    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
    颉
    1.38
    服务的
    1.27
    ánea
    1.21
    sime
    1.21
    хой
    1.20
    вающей
    1.19
    ünd
    1.16
    ắ
    1.15
    asket
    1.15
     tvor
    1.14
    POSITIVE LOGITS
    歹
    1.28
    Holder
    1.22
    PBS
    1.16
     pau
    1.12
    enson
    1.11
    henge
    1.10
     VHF
    1.08
    libraries
    1.08
    jupiter
    1.08
     supernovae
    1.07
    Activations Density 0.082%

    No Known Activations