© 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. 14053
    Prev
    Next
    INDEX
    Explanations

    Vienna, Austria

    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
    <bos>
    2.56
    axies
    2.54
    ્ન
    2.43
    ongoose
    2.37
    ératures
    2.31
    รง
    2.29
     officielles
    2.29
    charCode
    2.27
    alea
    2.27
    ocese
    2.27
    POSITIVE LOGITS
    ர்
    2.27
    ல்லை
    2.22
    ી
    2.22
    ר
    2.22
     உச்ச
    2.21
    ƈ
    2.18
    어서
    2.10
    tty
    2.02
    லி
    2.02
     불구
    2.00
    Activations Density 0.010%

    No Known Activations