© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4396
    Prev
    Next
    INDEX
    Explanations

    numbered items

    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_12_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
    3
    1.44
    2
    1.44
     очереди
    1.36
     relativity
    1.32
    zeit
    1.31
     reread
    1.30
    loride
    1.26
    anais
    1.26
     $\
    1.25
    4
    1.24
    POSITIVE LOGITS
     BELL
    1.47
     Crest
    1.46
     Eps
    1.43
     Hight
    1.42
     stein
    1.39
     Heel
    1.37
     sapon
    1.33
     Holm
    1.33
    dincer
    1.32
     Dorn
    1.32
    Activations Density 0.071%

    No Known Activations