© 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. 20145
    Prev
    Next
    INDEX
    Explanations

    organizational entities and concepts

    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
     Barca
    1.16
     Juve
    1.08
     Cavs
    1.04
     Philly
    0.94
     Barça
    0.91
     IVF
    0.91
     ICU
    0.91
     M
    0.91
     Dems
    0.88
     Bucs
    0.88
    POSITIVE LOGITS
     Verenigde
    0.99
    中华人民共和国
    0.95
     Organización
    0.95
     Escherichia
    0.94
     Universidade
    0.92
     meydana
    0.91
     Российской
    0.90
    秵
    0.89
     خداوند
    0.89
     Encyclopædia
    0.88
    Activations Density 0.668%

    No Known Activations