© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3912
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    }{}
    0.77
     {}
    0.63
    шая
    0.63
     bag
    0.61
    {}
    0.60
     theoretically
    0.59
     theoretical
    0.59
    وسی
    0.59
    Networking
    0.57
    Theoretical
    0.57
    POSITIVE LOGITS
     mathrm
    0.89
    ﾆ
    0.84
    normal
    0.81
    akkha
    0.79
     lipase
    0.78
    Bromo
    0.78
     норма
    0.77
     Ordin
    0.77
     quod
    0.76
     normale
    0.74
    Activations Density 0.019%

    No Known Activations