© 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. 8772
    Prev
    Next
    INDEX
    Explanations

    value of factor or rate

    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
    ائمة
    0.48
     piling
    0.42
     நின்
    0.41
    هِ
    0.40
     بر
    0.40
    داث
    0.40
    0
    0.40
    هههه
    0.40
     reheating
    0.40
    しっかり
    0.39
    POSITIVE LOGITS
    ૢ
    0.49
    ">'
    0.48
     которую
    0.48
    единенных
    0.48
    <0x86>
    0.48
     которые
    0.47
    эй
    0.47
     необходимых
    0.47
    izamos
    0.47
     которое
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.