© 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. 13044
    Prev
    Next
    INDEX
    Explanations

    victim, Virgin, sacrifice

    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
    arcz
    2.17
    phus
    2.08
    ǽ
    2.02
     assertThat
    1.99
    ښ
    1.95
    ご購入
    1.95
    ᔨ
    1.91
    Ⲁ
    1.90
    getahuan
    1.90
    꽃
    1.89
    POSITIVE LOGITS
     bluish
    1.70
     queue
    1.55
    btns
    1.51
     MER
    1.50
     দা
    1.49
     IMF
    1.48
     San
    1.46
     queues
    1.44
     B
    1.42
     SDP
    1.42
    Activations Density 0.074%

    No Known Activations