© 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. 19042
    Prev
    Next
    INDEX
    Explanations

    be using

    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
     essere
    0.84
     amicable
    0.82
     sentirse
    0.79
     被
    0.79
     dignified
    0.78
     intelligent
    0.77
     vibrant
    0.77
     excelente
    0.77
     adaptarse
    0.77
     brimming
    0.76
    POSITIVE LOGITS
    }}(
    0.65
    ેચ્છ
    0.65
    Trunc
    0.62
    ها
    0.62
    inverse
    0.60
    чения
    0.59
    తున్నారు
    0.59
    تے
    0.59
    Storing
    0.59
    是将
    0.58
    Activations Density 0.071%

    No Known Activations