© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13861
    Prev
    Next
    INDEX
    Explanations

    "what do you" questions

    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
    跹
    2.80
    te
    2.49
     móc
    2.47
    msqrt
    2.46
    iorari
    2.45
    ------------*/
    2.45
     m
    2.40
    weight
    2.37
    weighted
    2.34
    ************/
    2.34
    POSITIVE LOGITS
    ൻ
    2.98
    न
    2.92
    ndes
    2.90
     reim
    2.84
    ЗИ
    2.70
    अर
    2.64
    تو
    2.61
    軾
    2.59
    nych
    2.55
    列
    2.54
    Activations Density 0.012%

    No Known Activations