© 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. 4934
    Prev
    Next
    INDEX
    Explanations

    identifying descriptions

    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
    癱
    1.50
     بادشاہ
    1.48
    stvo
    1.45
    ły
    1.40
    ダメ
    1.39
    Buff
    1.37
     пока
    1.37
    闭
    1.36
    rück
    1.35
    down
    1.34
    POSITIVE LOGITS
     Evernote
    1.81
     emojis
    1.78
     tweet
    1.75
     AirPods
    1.69
     triples
    1.68
     WhatsApp
    1.68
     tuples
    1.68
     emoji
    1.64
     commas
    1.64
     numerator
    1.62
    Activations Density 0.007%

    No Known Activations