© 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. 4628
    Prev
    Next
    INDEX
    Explanations

    break up or down

    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
    せず
    0.85
    敢
    0.84
    amask
    0.82
    ísim
    0.82
    chop
    0.82
     Karo
    0.80
    lac
    0.79
    ísimo
    0.76
    锐
    0.76
     Peut
    0.76
    POSITIVE LOGITS
     predecessors
    1.34
    vascular
    1.30
     gemstones
    1.28
     Emeritus
    1.28
     ferns
    1.26
     slugs
    1.25
    ETERS
    1.25
     spectroscopic
    1.25
     vanes
    1.24
    iophene
    1.24
    Activations Density 0.074%

    No Known Activations