© 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. 202783
    Prev
    Next
    INDEX
    Explanations

    The explanation for the neuron's behavior is:all and especially leads

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

    components list items

    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
    ף
    0.46
    translations
    0.46
    ම
    0.46
    딤
    0.46
    没
    0.45
    ্জ
    0.45
    ᱐
    0.45
    ቃል
    0.45
    ্ক
    0.44
    לות
    0.44
    POSITIVE LOGITS
     Rajasthan
    0.56
     เพียง
    0.47
     A
    0.46
     ကြ
    0.46
     木
    0.45
     เชื่อ
    0.45
     rä
    0.45
     Maschine
    0.44
     บน
    0.44
    فرم
    0.44
    Activations Density 0.001%

    No Known Activations