© 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. 13550
    Prev
    Next
    INDEX
    Explanations

    like all [category]

    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
    te
    2.21
    €™
    2.13
    ๊ะ
    2.08
    ta
    1.92
    籁
    1.89
    ellate
    1.88
    -
    1.82
    ***
    1.80
    ellum
    1.80
    nellement
    1.79
    POSITIVE LOGITS
    මණ
    2.50
    एक
    2.48
    सारा
    2.35
    佢
    2.34
    स
    2.31
    ूपी
    2.31
    ಟಕ
    2.31
    룻
    2.25
    ಟನೆ
    2.24
    еш
    2.23
    Activations Density 0.000%

    No Known Activations