© 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-262K
    7. 147712
    Prev
    Next
    INDEX
    Explanations

    Be specific

    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_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
    pping
    0.74
    人了
    0.72
     propriedade
    0.71
    ">&#
    0.70
    ছো
    0.70
    penas
    0.68
     вона
    0.67
    鏂
    0.67
    Sliced
    0.66
     proprietà
    0.66
    POSITIVE LOGITS
     thrombosis
    0.81
     dissection
    0.80
    mailer
    0.79
     comerciais
    0.79
    ออก
    0.77
     zmieni
    0.76
     herpes
    0.76
     flora
    0.76
     قار
    0.76
     apartheid
    0.75
    Activations Density 0.000%

    No Known Activations