© 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. 11019
    Prev
    Next
    INDEX
    Explanations

    concept / state description

    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
     实现
    2.53
     資料
    2.48
    <0x1E>
    2.42
     myfile
    2.39
     劉
    2.38
     textAlign
    2.36
    
    2.32
     項
    2.30
     translateX
    2.29
    瀝
    2.29
    POSITIVE LOGITS
    হারা
    1.62
    Always
    1.59
    1
    1.58
    aya
    1.50
    ay
    1.49
    aw
    1.48
    ama
    1.47
    aa
    1.47
    amenti
    1.46
    ým
    1.45
    Activations Density 0.000%

    No Known Activations