© 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. 969
    Prev
    Next
    INDEX
    Explanations

    edged sword; charts

    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
    แปลง
    1.60
    필
    1.55
     อื่น
    1.42
    FAKE
    1.40
     ประเภท
    1.39
    ประเภท
    1.39
    (',',$
    1.39
    อย่า
    1.38
    COMMENT
    1.38
    '=>'','
    1.37
    POSITIVE LOGITS
    idação
    1.57
     coincides
    1.51
     treacher
    1.38
    ungs
    1.34
     competes
    1.33
     reddish
    1.32
    sis
    1.31
     predecessor
    1.30
    ämme
    1.30
     antisymmetric
    1.30
    Activations Density 0.000%

    No Known Activations