© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4559
    Prev
    Next
    INDEX
    Explanations

    unforgiving land

    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_24_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
     süd
    0.81
     tenga
    0.76
     nelle
    0.74
     dalam
    0.73
     მე
    0.71
     bassa
    0.70
     tinggi
    0.70
    Ü
    0.70
     باشد
    0.69
     makanan
    0.69
    POSITIVE LOGITS
    сунок
    0.77
     принято
    0.74
     INNOV
    0.73
     Novosibirsk
    0.72
     времени
    0.71
     VLAN
    0.71
     Dl
    0.70
    SEQUENCE
    0.70
     Sarajevo
    0.70
    䡆
    0.70
    Activations Density 0.001%

    No Known Activations