© 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. 2953
    Prev
    Next
    INDEX
    Explanations

    model created by

    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
    along
    1.48
    minus
    1.46
    他に
    1.45
     Minus
    1.44
     усіх
    1.42
    prima
    1.40
    asting
    1.39
    ===========
    1.38
    hum
    1.37
     კომ
    1.36
    POSITIVE LOGITS
     cyclotron
    0.84
     passi
    0.84
    址
    0.80
    prüsü
    0.78
    驚
    0.78
    彫
    0.76
    buildCommand
    0.76
    estay
    0.76
     ليش
    0.75
    ütü
    0.73
    Activations Density 0.064%

    No Known Activations