© 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. 721
    Prev
    Next
    INDEX
    Explanations

    helpline phone numbers

    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
     CO
    0.72
     hipp
    0.72
     GMO
    0.69
     Soyuz
    0.67
    敬
    0.67
     exper
    0.66
    SCO
    0.65
     সুল
    0.65
     Hipp
    0.65
     bij
    0.64
    POSITIVE LOGITS
    
    0.68
     სტ
    0.65
    SetParameter
    0.65
    десят
    0.61
     जरिए
    0.60
    ftar
    0.60
     خواہ
    0.60
     Archivado
    0.59
     اگ
    0.59
     어린이
    0.59
    Activations Density 0.052%

    No Known Activations