© 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. 13-GEMMASCOPE-2-RES-16K
    7. 513
    Prev
    Next
    INDEX
    Explanations

    addressing user needs or intentions

    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_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
     _{(
    0.79
    พื้น
    0.77
     наших
    0.76
     коэффици
    0.76
     ช่อง
    0.74
    ความ
    0.73
     катего
    0.73
    它们的
    0.72
     количества
    0.71
     .{
    0.70
    POSITIVE LOGITS
     himself
    1.18
     spoke
    1.09
     insisted
    1.08
     believes
    1.05
     apologized
    1.05
     chose
    1.04
     insists
    1.01
     reiterated
    0.99
     speaks
    0.99
     knew
    0.98
    Activations Density 3.235%

    No Known Activations