© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11644
    Prev
    Next
    INDEX
    Explanations

    adding more

    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
    ளாக்
    1.83
    არ
    1.82
    سی
    1.82
    デア
    1.78
    ac
    1.77
    ​
    1.75
    ೊಳ
    1.74
    高于
    1.74
    
    1.74
    ුව
    1.72
    POSITIVE LOGITS
    iin
    2.48
    此之外
    2.36
    ेर
    2.26
    הר
    2.20
    ה
    2.16
    esz
    2.15
    anah
    2.08
    a
    2.01
    aaaa
    2.01
    iis
    1.99
    Activations Density 0.061%

    No Known Activations