© 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. 10761
    Prev
    Next
    INDEX
    Explanations

    would like

    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
     żół
    1.06
    ందించ
    0.98
    飧
    0.97
    cud
    0.97
     कोषा
    0.96
     разнообраз
    0.96
    楽しく
    0.95
    ㄵ
    0.94
     Dank
    0.93
     Think
    0.92
    POSITIVE LOGITS
     like
    1.93
    like
    1.74
     Like
    1.57
    Like
    1.54
     LIKE
    1.41
    LIKE
    1.29
    likes
    1.19
     seperti
    1.12
     như
    1.10
     como
    1.09
    Activations Density 0.072%

    No Known Activations