© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2192
    Prev
    Next
    INDEX
    Explanations

    achieving goals

    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
     exposing
    0.89
    Description
    0.86
    정
    0.85
     counterpart
    0.85
     background
    0.84
     avenues
    0.84
     individuals
    0.84
    exposure
    0.83
    rogate
    0.82
     exposure
    0.82
    POSITIVE LOGITS
     எனப்படும்
    1.24
    (.*
    1.19
    迺
    1.19
     scegli
    1.18
     című
    1.15
     revista
    1.13
     cloro
    1.13
    李
    1.12
     vyroben
    1.11
     czyli
    1.10
    Activations Density 0.730%

    No Known Activations