© 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. 13-GEMMASCOPE-2-RES-65K
    4. 2073
    Prev
    Next
    INDEX
    Explanations

    multi-lingual prefixes and beginnings

    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_13_width_65k_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
    ishly
    0.88
    ically
    0.81
    iously
    0.78
    istically
    0.77
    9
    0.75
    fully
    0.70
    ously
    0.69
    lessly
    0.67
    igen
    0.66
     a
    0.65
    POSITIVE LOGITS
    𒀊
    0.98
     vrch
    0.97
    éristique
    0.96
    𒆷
    0.95
    URNIZ
    0.94
    𒊑
    0.93
    guồn
    0.93
    𒋫
    0.92
     குதிக
    0.92
    밂
    0.92
    Activations Density 0.075%

    No Known Activations