© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14935
    Prev
    Next
    INDEX
    Explanations

    den followed by time or nouns

    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_7_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
    𝗮
    3.56
    𝗺
    3.33
    ��
    2.80
    𝘁
    2.80
    𝗹
    2.78
    𝘆
    2.70
    𝗵
    2.65
    ellant
    2.60
    𝘀
    2.60
    𝗴
    2.60
    POSITIVE LOGITS
    ר
    2.59
    ी
    2.59
    ील
    2.43
    어서
    2.36
    oop
    2.25
    Incremental
    2.25
    ecek
    2.25
    ে
    2.24
    e
    2.24
    eek
    2.24
    Activations Density 0.019%

    No Known Activations