© 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. 4880
    Prev
    Next
    INDEX
    Explanations

    learning paths and resources

    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
    ૂર્ણ
    0.67
    ari
    0.66
    atore
    0.66
    umm
    0.65
    今天
    0.65
    ਇ
    0.65
    きの
    0.64
    Trent
    0.64
    них
    0.64
    atas
    0.64
    POSITIVE LOGITS
     menores
    0.77
    ược
    0.75
    ,}$
    0.75
    ี้
    0.73
    };
    0.70
     вклю
    0.70
     lograr
    0.69
    ,}
    0.68
     publicized
    0.68
     keing
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.