© 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. 1092
    Prev
    Next
    INDEX
    Explanations

    similarity and comparison

    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
    ken
    2.38
    ,"
    2.28
    𝘯
    2.21
    "'
    2.06
    𝘬
    2.06
    SUS
    2.06
    K
    2.02
     '
    2.01
    ;"
    1.97
    ت
    1.96
    POSITIVE LOGITS
    exact
    2.10
     exact
    2.08
    mousePressed
    2.03
     একইভাবে
    1.99
     proportionately
    1.97
    ulado
    1.96
    assertSame
    1.95
     सुझा
    1.89
    uptools
    1.88
     gleiche
    1.86
    Activations Density 0.751%

    No Known Activations