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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31920
    Prev
    Next
    INDEX
    Explanations

    Did anyone ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FACTS
    0.78
    є
    0.76
     MAPK
    0.75
    тих
    0.75
     остров
    0.75
     Михаил
    0.75
     LMFBR
    0.74
    𝔱
    0.73
     BENEFITS
    0.72
     ﺍﻟ
    0.71
    POSITIVE LOGITS
     gérer
    0.84
     indien
    0.83
     ao
    0.80
     attitude
    0.80
     ajo
    0.80
     als
    0.78
     gjort
    0.78
     existe
    0.76
     rencontrer
    0.75
     mia
    0.73
    Activations Density 0.000%

    No Known Activations