© 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-262K
    7. 2826
    Prev
    Next
    INDEX
    Explanations

    for clarity or reason

    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_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
    ة
    0.71
    ת
    0.62
    Pentru
    0.59
    For
    0.56
    With
    0.55
    А
    0.54
    Un
    0.51
    If
    0.51
    ed
    0.51
    N
    0.50
    POSITIVE LOGITS
     instance
    0.85
     example
    0.81
     sake
    0.81
     purposes
    0.80
    erun
    0.75
     reasons
    0.74
     awhile
    0.73
    geries
    0.69
     starters
    0.67
     sure
    0.66
    Activations Density 0.514%

    No Known Activations