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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5577
    Prev
    Next
    INDEX
    Explanations

    in terms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
     infine
    0.77
     κο
    0.70
    ﻛ
    0.70
    ことにより
    0.69
     anteriormente
    0.68
     guten
    0.68
     sonra
    0.65
     recientemente
    0.65
     Guten
    0.65
     Eisenhower
    0.64
    POSITIVE LOGITS
    rels
    0.93
     ratios
    0.88
     mattered
    0.85
     Mileage
    0.82
    iculation
    0.80
     بالنسبة
    0.78
     therapists
    0.77
    |,
    0.77
     deities
    0.76
    身材
    0.75
    Activations Density 0.041%

    No Known Activations