© 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. 2206
    Prev
    Next
    INDEX
    Explanations

    set up

    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
     getc
    1.21
    )^{[\
    1.19
     Plenum
    1.14
     saluto
    1.13
    ineau
    1.01
    使
    1.01
     myśl
    1.01
     $<\
    1.00
    setInput
    0.99
    льзова
    0.99
    POSITIVE LOGITS
     aside
    2.80
     alight
    2.41
     ablaze
    2.34
    TLE
    2.29
    tle
    2.23
    aside
    2.15
    alian
    2.15
     timers
    2.11
     adrift
    2.11
     apart
    2.11
    Activations Density 0.186%

    No Known Activations