© 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. 549
    Prev
    Next
    INDEX
    Explanations

    at + time or stage

    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
    于
    0.90
    moire
    0.88
    acyl
    0.88
     গোয়
    0.83
    acaks
    0.82
    ivalent
    0.81
    эрэг
    0.80
     використову
    0.80
    dem
    0.80
    ㆍ
    0.79
    POSITIVE LOGITS
     least
    2.32
    least
    1.94
    Least
    1.65
     Least
    1.57
     behest
    1.49
    ravés
    1.42
     outset
    1.36
    rocities
    1.31
     lunchtime
    1.31
     dusk
    1.29
    Activations Density 0.639%

    No Known Activations