© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1352
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
     considérable
    2.01
    ement
    1.88
    ഹു
    1.84
    يا
    1.74
    a
    1.70
    𝕞
    1.67
    Ok
    1.65
    𝒉
    1.65
     địa
    1.65
    e
    1.64
    POSITIVE LOGITS
    <unused1046>
    2.49
     fpr
    2.46
     于
    2.40
    <unused1030>
    2.39
     به
    2.38
    ClCompile
    2.36
    <unused985>
    2.32
    <unused411>
    2.31
     $-$
    2.31
    于
    2.30
    Activations Density 1.077%

    No Known Activations