© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 302
    Prev
    Next
    INDEX
    Explanations

    looking at or for

    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_17_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
     অবস্থানের
    0.86
    talet
    0.84
    urança
    0.82
     অবস্থান
    0.81
    જા
    0.81
    ਜ
    0.80
    知道了
    0.77
     छूट
    0.77
    டம்
    0.76
     переменных
    0.76
    POSITIVE LOGITS
     intently
    1.43
     at
    1.42
     atthe
    1.35
     attentively
    1.28
     atent
    1.21
     👀
    1.13
     nervously
    1.11
     keenly
    1.06
     atth
    1.05
     curiously
    1.05
    Activations Density 0.689%

    No Known Activations