© 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. 602
    Prev
    Next
    INDEX
    Explanations

    if you'd like offers

    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
     عشان
    1.26
    /
    1.18
    to
    1.12
     علشان
    1.08
    up
    1.03
    aux
    1.00
    and
    0.98
     পেল
    0.95
    s
    0.95
    au
    0.94
    POSITIVE LOGITS
     be
    1.82
     adhere
    1.80
     undertake
    1.76
     behave
    1.74
     surpass
    1.71
     undergo
    1.70
     operate
    1.68
     engage
    1.67
     provide
    1.67
     administer
    1.67
    Activations Density 1.356%

    No Known Activations