© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2033
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    𝐡
    3.12
    en
    2.71
    𝐨
    2.66
    𝐫
    2.57
    𝐬
    2.50
    rey
    2.48
    𝐧
    2.46
    aard
    2.40
    arli
    2.39
    𝐚
    2.39
    POSITIVE LOGITS
    紝
    3.01
    бто
    2.52
    ্শন
    2.42
    трима
    2.28
    ்த்து
    2.27
    साई
    2.24
     quadrado
    2.21
    тріш
    2.19
    ்ட
    2.16
    amides
    2.13
    Activations Density 0.595%

    No Known Activations