© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6155
    Prev
    Next
    INDEX
    Explanations

    stirring and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    at
    2.24
    د
    2.22
    <bos>
    2.16
    Ӏо
    2.10
    Quote
    2.09
    es
    2.08
    arini
    2.07
    surprisingly
    2.06
    atud
    2.03
    amante
    2.02
    POSITIVE LOGITS
    ้
    2.16
    ニャ
    2.05
     thisComponent
    2.02
    কালীন
    2.02
    𝘃
    2.00
    ds
    2.00
    ́t
    1.94
    DebugSymbols
    1.91
    𝗱
    1.91
    Ὁ
    1.90
    Activations Density 0.003%

    No Known Activations