© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7375
    Prev
    Next
    INDEX
    Explanations

    more advanced implementations

    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
     fullest
    0.88
     furthest
    0.88
    蜷
    0.87
    odoro
    0.87
     透
    0.86
     strata
    0.85
     여기까지
    0.84
    最
    0.84
    辿
    0.83
    𝗢
    0.82
    POSITIVE LOGITS
    replaced
    1.89
     replaced
    1.88
     vervangen
    1.75
     replace
    1.71
    replace
    1.66
     replaces
    1.66
     reemplazar
    1.64
     replacements
    1.64
     заменить
    1.62
     reempl
    1.60
    Activations Density 0.277%

    No Known Activations