© 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. 1068
    Prev
    Next
    INDEX
    Explanations

    from origin or source

    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
    ExpNow
    2.49
    ็ว
    2.48
    စု
    2.13
    clipse
    2.11
    giene
    2.08
    
    2.02
    針
    2.01
    lijke
    1.97
    loat
    1.97
    न
    1.97
    POSITIVE LOGITS
    ባድ
    3.67
    𝐩
    3.10
    𝐦
    3.07
    ্প্র
    3.02
    𝓬
    2.90
     infancy
    2.84
     सटे
    2.83
    __(/*!
    2.82
    𝐟
    2.78
     thence
    2.72
    Activations Density 0.747%

    No Known Activations