© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10132
    Prev
    Next
    INDEX
    Explanations

    Sentiment Analysis

    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
     പഴയ
    1.01
    鐫
    0.89
     അടുത്ത
    0.89
    defini
    0.86
     envis
    0.85
     içeren
    0.85
    anterie
    0.85
    旧
    0.84
     envisions
    0.83
     estabelecer
    0.83
    POSITIVE LOGITS
    jasper
    0.87
     teenager
    0.87
     rapaz
    0.86
    iai
    0.84
    aing
    0.83
     Teen
    0.83
    Teen
    0.83
     jus
    0.82
     medie
    0.82
     radiolysis
    0.81
    Activations Density 0.051%

    No Known Activations