© 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. 148162
    Prev
    Next
    INDEX
    Explanations

    past state changes

    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
    Transc
    0.85
    arrive
    0.73
    Cou
    0.73
    Grunge
    0.70
     emerge
    0.70
    ◃
    0.69
     unserer
    0.69
    層
    0.67
    ફળ
    0.66
    árl
    0.66
    POSITIVE LOGITS
     needed
    1.00
     changed
    0.89
     saw
    0.88
     sees
    0.88
     necessário
    0.88
     necesario
    0.87
     underwent
    0.85
     adjusted
    0.85
     reimbursed
    0.82
    得到了
    0.82
    Activations Density 0.028%

    No Known Activations