© 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. 223172
    Prev
    Next
    INDEX
    Explanations

    descriptive states or outcomes

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

    conditional situations or abstract concepts

    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
    PUBLIC
    0.48
    nEnter
    0.48
    ある
    0.47
    PY
    0.46
     길
    0.45
     volgen
    0.45
    
    0.44
    SU
    0.44
    ุก
    0.44
    َ
    0.44
    POSITIVE LOGITS
     enlightened
    0.53
     комплект
    0.52
     corrupted
    0.51
     treasured
    0.50
     Địa
    0.48
    ্লেখ
    0.47
     hydrated
    0.47
     anointed
    0.47
     blessed
    0.47
     translucent
    0.46
    Activations Density 0.001%

    No Known Activations