© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5245
    Prev
    Next
    INDEX
    Explanations

    engineering and statistics

    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_13_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
    ٔ
    1.29
    amers
    1.26
    -'
    1.19
    اطع
    1.18
    utz
    1.16
     отече
    1.15
    italization
    1.13
    oop
    1.10
    eper
    1.10
    
    1.10
    POSITIVE LOGITS
     leaning
    1.51
     波
    1.50
    रो
    1.47
     twinkling
    1.45
    Sunflower
    1.45
     Waves
    1.42
    𝒕
    1.41
     humming
    1.37
     wavy
    1.33
     ミ
    1.33
    Activations Density 0.000%

    No Known Activations