© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4471
    Prev
    Next
    INDEX
    Explanations

    provides something

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of verbs that denote providing or offering something (e.g., “provides,” “provided,” “offering”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     l
    1.14
     dyes
    1.13
    ꯑ
    1.11
     kotlinx
    1.10
     flange
    1.09
    ઓની
    1.09
    భర
    1.09
    AR
    1.07
    EL
    1.04
    లపై
    1.04
    POSITIVE LOGITS
    ли
    1.26
    iatric
    1.23
     insight
    1.20
    یا
    1.20
    ឲ
    1.20
    ්
    1.17
     کردہ
    1.16
    ل
    1.16
    сё
    1.14
     바랍니다
    1.12
    Activations Density 0.149%

    No Known Activations