© 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. 9290
    Prev
    Next
    INDEX
    Explanations

    individual self-reliance and need

    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_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
     nuovo
    0.97
     পূ
    0.96
     affections
    0.91
     nuova
    0.88
     rinnov
    0.87
     نئے
    0.86
    Ĉ
    0.85
     nuovi
    0.84
    関連
    0.84
    溶解
    0.84
    POSITIVE LOGITS
     hindsight
    1.31
    ઓએ
    1.30
    indsight
    1.09
     HAD
    1.05
     wisely
    1.03
     правильно
    1.03
     foresight
    1.03
    选择了
    1.02
    咎
    1.01
     overestimated
    1.01
    Activations Density 0.318%

    No Known Activations