© 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. 4840
    Prev
    Next
    INDEX
    Explanations

    http:// and https://

    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
     windfall
    1.43
    entuan
    1.38
    〕
    1.31
    lamydia
    1.26
    átiles
    1.23
     Wnd
    1.22
     sebagainya
    1.21
     menengah
    1.20
     sympathies
    1.19
    angaroo
    1.19
    POSITIVE LOGITS
    сам
    1.29
    钦
    1.25
    努
    1.22
    ver
    1.18
    entries
    1.17
     synov
    1.17
    rek
    1.16
    vor
    1.16
     capture
    1.16
    真实
    1.15
    Activations Density 0.005%

    No Known Activations