© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    more than

    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
     buenos
    1.46
     buen
    1.34
     dönt
    1.21
     guter
    1.18
     buenas
    1.17
     Qaraldi
    1.16
    ^(
    1.15
    🆈
    1.14
     Certaines
    1.12
     bons
    1.08
    POSITIVE LOGITS
     than
    4.16
    Than
    3.48
    than
    3.38
     Than
    3.15
     niż
    3.01
     än
    2.97
     kuin
    2.79
     THAN
    2.73
     daripada
    2.59
     importantly
    2.56
    Activations Density 0.431%

    No Known Activations