© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8424
    Prev
    Next
    INDEX
    Explanations

    new sentence starts

    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_17_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
     предотвра
    1.24
     prevenção
    1.06
     prevents
    1.04
     intolerable
    1.04
     situações
    1.02
    㳓
    1.02
     hurting
    1.00
    綘
    0.99
     worsens
    0.99
     déprimées
    0.99
    POSITIVE LOGITS
     well
    0.76
     thumbs
    0.74
     Worth
    0.71
     Take
    0.69
    hint
    0.68
     par
    0.68
    굳
    0.67
     had
    0.66
     kindly
    0.65
     extra
    0.65
    Activations Density 1.439%

    No Known Activations