© 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. 862
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    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
    REQUEST
    3.00
    ㄻ
    2.59
    睫
    2.55
    よし
    2.54
    د
    2.51
    REGI
    2.50
    岖
    2.49
    아요
    2.46
    ну
    2.45
    ThreadGroup
    2.44
    POSITIVE LOGITS
    bies
    3.05
    ה
    2.60
    een
    2.25
    ej
    2.18
    ois
    2.17
    aal
    2.17
    yas
    2.16
    yah
    2.13
    τητα
    2.13
    zes
    2.12
    Activations Density 0.389%

    No Known Activations