© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116250
    Prev
    Next
    INDEX
    Explanations

    ordering, consequences, aim, receive

    np_acts-logits-general · gemini-2.5-flash-lite

    conditions, requirements, principles, benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setups
    0.43
     homogenization
    0.43
     feeling
    0.43
     അ
    0.43
     hallways
    0.43
    把它
    0.41
     stupidity
    0.41
     ł
    0.40
     tulle
    0.40
     raio
    0.40
    POSITIVE LOGITS
     чемпи
    0.48
    今年的
    0.47
    интере
    0.46
     올해
    0.45
    пуляр
    0.45
    িক্ত
    0.44
     সাম্প্রতিক
    0.43
    émica
    0.43
     escolh
    0.43
    assati
    0.43
    Activations Density 0.001%

    No Known Activations