© 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. 2017
    Prev
    Next
    INDEX
    Explanations

    Japan

    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
     ভট্ট
    0.93
    춧
    0.90
    駱
    0.87
     Walth
    0.85
     FileMode
    0.84
    蘅
    0.84
    cailles
    0.83
     inhalation
    0.83
    鄂
    0.83
     Riggs
    0.82
    POSITIVE LOGITS
     JC
    3.00
     JJ
    3.00
     JB
    2.92
     JM
    2.90
    JE
    2.89
     JD
    2.89
     JF
    2.86
     JT
    2.85
     JW
    2.82
     Ju
    2.81
    Activations Density 1.229%

    No Known Activations