© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6071
    Prev
    Next
    INDEX
    Explanations

    python class initialization

    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
     Burroughs
    1.59
     Correctional
    1.44
     firef
    1.41
    炊
    1.39
    urkan
    1.38
    埚
    1.36
     Guant
    1.35
    كذا
    1.33
     dara
    1.29
     desple
    1.29
    POSITIVE LOGITS
     artist
    1.60
     immuno
    1.49
     antiqu
    1.44
     artists
    1.38
     art
    1.36
     hydro
    1.36
    (+
    1.36
    phar
    1.36
     antiques
    1.35
     attraction
    1.35
    Activations Density 0.001%

    No Known Activations