© 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. 1452
    Prev
    Next
    INDEX
    Explanations

    option 1

    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
     (#
    0.90
     (
    0.85
     somehow
    0.80
     [@
    0.80
     ($
    0.80
     (*
    0.78
     little
    0.75
     squares
    0.73
    metics
    0.73
     ((
    0.71
    POSITIVE LOGITS
    étaire
    0.85
     biodivers
    0.83
    地域
    0.82
    ा
    0.81
     地域
    0.80
     plein
    0.80
    ӥ
    0.80
    :")
    0.79
     terroir
    0.79
    最
    0.79
    Activations Density 0.037%

    No Known Activations