© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3926
    Prev
    Next
    INDEX
    Explanations

    actions and state changes

    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_31_width_16k_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
     cavalry
    0.65
    Mrs
    0.63
    Tcp
    0.61
     हाइड्रो
    0.60
     mrs
    0.60
     फैली
    0.58
     derby
    0.57
    靑
    0.57
     infantry
    0.56
     plexus
    0.56
    POSITIVE LOGITS
     изначально
    0.78
     purposefully
    0.75
     также
    0.72
     напрямую
    0.71
     Также
    0.70
     LGBTQ
    0.66
     inclusivity
    0.66
     impactful
    0.66
     also
    0.65
     rámci
    0.65
    Activations Density 0.091%

    No Known Activations