© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    close or proximity

    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
    ی
    3.24
    𝙚
    2.98
    emek
    2.92
    ubah
    2.91
    色列
    2.86
    ių
    2.78
    চাল
    2.78
    नं
    2.74
    sman
    2.72
    tım
    2.70
    POSITIVE LOGITS
    Hash
    2.71
    =")"
    2.59
    comp
    2.57
    లీ
    2.56
    ாஹ
    2.55
    லி
    2.54
     dispel
    2.52
    ඝ
    2.42
    SIGN
    2.42
    𝑙
    2.36
    Activations Density 0.060%

    No Known Activations