© 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. 87914
    Prev
    Next
    INDEX
    Explanations

    words followed by common verbs or prepositions

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

    my own analysis and experience

    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
    SuppressWarnings
    0.52
    igheid
    0.50
     Kampf
    0.48
    ;%(
    0.44
    мость
    0.44
     MANAGEMENT
    0.44
     Nutzung
    0.43
     Handlung
    0.43
     выполнение
    0.43
    ↵↵
    0.43
    POSITIVE LOGITS
     nematode
    0.47
     lipids
    0.44
     tad
    0.43
     arb
    0.43
     mite
    0.42
     webcast
    0.42
    ลิ
    0.42
     surcharge
    0.42
     tentacles
    0.42
     bros
    0.41
    Activations Density 0.000%

    No Known Activations