© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10819
    Prev
    Next
    INDEX
    Explanations

    really + adjective describing a question

    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_22_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
    也会
    0.85
    া
    0.85
     likely
    0.84
    এছ
    0.79
     meanwhile
    0.76
    นี
    0.75
    likely
    0.75
    แน่นอน
    0.73
    ljiv
    0.71
     वायरल
    0.71
    POSITIVE LOGITS
     ought
    1.47
    <unused257>
    1.30
     trebuie
    1.27
     Trebuie
    1.24
     Shouldn
    1.23
     struggling
    1.22
    仅
    1.21
     только
    1.20
     tylko
    1.19
     सिर्फ
    1.19
    Activations Density 0.077%

    No Known Activations