© 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. 34381
    Prev
    Next
    INDEX
    Explanations

    magazine or magazines

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

    Smithsonian Magazine URLs

    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
     monotonic
    0.55
     monotonically
    0.47
     shinobi
    0.46
    StringSet
    0.44
    تحانات
    0.44
    ستوى
    0.44
     deterministic
    0.43
    
    0.43
     inputted
    0.42
    MakeRange
    0.42
    POSITIVE LOGITS
     magazine
    1.32
     MAGAZINE
    1.20
     Magazine
    1.18
    Magazine
    1.16
    magazine
    1.13
    杂志
    1.08
     magazines
    1.06
     Magazines
    0.92
     magaz
    0.88
     MAGAZ
    0.81
    Activations Density 0.199%

    No Known Activations