© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6037
    Prev
    Next
    INDEX
    Explanations

    AI tool and platform names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
    FIFA
    0.81
     YouTube
    0.81
     Wikimedia
    0.81
     harassing
    0.79
    琨
    0.77
     Merck
    0.77
     MacOS
    0.76
     FIFA
    0.75
     Sony
    0.75
     Evolution
    0.74
    POSITIVE LOGITS
    रोग
    0.61
    后的
    0.58
    aisseur
    0.58
     hydrophobic
    0.58
     عف
    0.58
     বয়
    0.57
    }}}{\
    0.57
    convert
    0.57
    édon
    0.56
     দ্ব
    0.55
    Activations Density 0.046%

    No Known Activations