© 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. 254
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     リ
    0.83
     तिवारी
    0.82
     ラ
    0.79
     ジ
    0.79
     テーブル
    0.75
     від
    0.74
     кг
    0.74
     オ
    0.74
     /
    0.73
     =
    0.73
    POSITIVE LOGITS
     undesirable
    1.25
     detrimental
    1.18
     zusätzliche
    1.18
     shortcomings
    1.17
     drastic
    1.16
     momentous
    1.15
     discrepancies
    1.13
     ulterior
    1.12
    <unused1252>
    1.12
     deleterious
    1.09
    Activations Density 5.912%

    No Known Activations