© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 115061
    Prev
    Next
    INDEX
    Explanations

    multilingual text segments

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

    political security discourse

    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
     Thermodynamics
    0.52
     thermique
    0.48
     thermodynamics
    0.48
     auricular
    0.47
     ग्लूको
    0.47
    두
    0.47
     थर्मल
    0.47
    بھی
    0.46
    وست
    0.44
     δύο
    0.44
    POSITIVE LOGITS
    йда
    0.44
    কেন্ড
    0.42
     Empower
    0.42
    炇
    0.40
    ំណ
    0.39
    繼續
    0.39
    尚未
    0.39
     empower
    0.39
    ddagger
    0.39
    ährt
    0.38
    Activations Density 0.002%

    No Known Activations