© 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. 6420
    Prev
    Next
    INDEX
    Explanations

    grammatical endings and connectors

    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
     nonfiction
    1.57
     parsing
    1.55
    stopPropagation
    1.53
    ༅
    1.53
    сылка
    1.52
    OLOGIE
    1.52
    غام
    1.52
    ༄
    1.51
     rumors
    1.50
     rumor
    1.49
    POSITIVE LOGITS
     satisfied
    1.39
    <eos>
    1.38
     interf
    1.24
     against
    1.24
    ROY
    1.23
    uj
    1.21
    ieved
    1.20
     outperformed
    1.19
    utherland
    1.17
     Trafalgar
    1.17
    Activations Density 0.006%

    No Known Activations