© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    recognize and speculate

    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
    UNDS
    1.81
    𝓱
    1.79
    𝓹
    1.76
    ێن
    1.72
     '-
    1.68
    ⃛
    1.67
    ὔ
    1.65
    𝓵
    1.65
    ਹ
    1.65
    ALITY
    1.59
    POSITIVE LOGITS
    ي
    2.14
    iak
    2.09
    تس
    1.96
    ここでは
    1.93
    ம்
    1.92
    yı
    1.91
    rün
    1.89
    y
    1.84
    ligence
    1.83
    ರುಗ
    1.82
    Activations Density 0.159%

    No Known Activations