© 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. 871
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    S
    3.20
    ge
    2.67
    E
    2.51
    plib
    2.47
    Pra
    2.41
    ogs
    2.40
    čiau
    2.31
    C
    2.25
    xymatrix
    2.23
     doi
    2.23
    POSITIVE LOGITS
    Ạ
    3.14
    ิมพ์
    3.02
    melon
    2.99
    ATTLE
    2.92
    USING
    2.89
    ЕР
    2.89
    szyst
    2.88
    ﾙ
    2.86
    OLF
    2.84
    ICK
    2.84
    Activations Density 1.031%

    No Known Activations