© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 219246
    Prev
    Next
    INDEX
    Explanations

    dating or personal detail

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

    reading, advantage, inexpensive

    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
    
    0.47
    ាន់
    0.46
    悵
    0.46
     komplex
    0.45
     CONSTRAINT
    0.43
     mysql
    0.43
    蠶
    0.43
    人們
    0.43
     rong
    0.43
     اخذت
    0.42
    POSITIVE LOGITS
     Boley
    0.47
     season
    0.46
     faith
    0.43
    ต่อเนื่อง
    0.43
     soldier
    0.43
    Faith
    0.42
    Season
    0.41
    㶲
    0.41
     savoir
    0.41
     冬
    0.41
    Activations Density 0.000%

    No Known Activations