© 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. 22-GEMMASCOPE-2-RES-16K
    7. 855
    Prev
    Next
    INDEX
    Explanations

    technical explanations and programming

    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_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
    slip
    0.80
    했
    0.72
    Silence
    0.71
    zeros
    0.68
    Sincerely
    0.67
    sk
    0.67
    Ja
    0.67
    insert
    0.67
    此处
    0.66
    Мне
    0.65
    POSITIVE LOGITS
     playgrounds
    0.91
     RFC
    0.87
     MongoDB
    0.84
     Haupt
    0.83
     VMware
    0.82
     libraries
    0.82
     []*
    0.81
     Vienne
    0.81
     upperBound
    0.81
    ȩ
    0.80
    Activations Density 0.322%

    No Known Activations